CONTEXT PRESERVATION FOR SYNTHETIC IMAGE ENLARGEMENT USING DIFFUSION

Abstract

The approaches presented here relate to generating synthetic images with one or more augmentations that are realistically added to objects within the images, while ensuring the preservation and integrity of semantic or contextual information within the image. A synthetic augmentation system can identify and extract foreground image data (e.g., text), and a version of the image with the foreground data removed can be processed by a generative diffusion model. One or more inputs can be provided to specify aspects such as the type or strength of the augmentation to be performed. After an augmented image has been generated using the generative diffusion model, the previously removed text can be reintroduced into the image.A synthetic augmentation system can use one or more text fade-in weights, such as a defect fade-in weight and a letter fade-in weight. The final result is an image with added realistic augmentations that preserves the semantic content.

Description

BACKGROUND

[0001] There are various operations or tasks related to animation or training data generation for which realistic image augmentation is beneficial. For example, it may be advantageous when training a machine learning model to include training data representative of a number of different situations or conditions. Building accurate and robust deep learning models for tasks such as image recognition and interpretation may require training on datasets that mimic the great diversity and imperfections seen in the real world. One of the key challenges in this field is currently the lack of sufficiently diverse and imperfect data that reflect real-world conditions.For example, a three-dimensional (3D) representation of a road sign or vehicle used for training may be flawless, but in the real world, these objects often exhibit defects such as rust, dirt, raindrops, damage, or even graffiti. These imperfections can severely impact the performance of models trained on data where such conditions are not or rarely manifest.Generative machine learning models can be used to synthesize images that represent at least some of these states, but models such as generative diffusion models can introduce transformations that may undesirably change the appearance or context of an object, such as by modifying text on a sign to which an augmentation is added, which can then affect the realism of the object as well as the quality of a machine learning model trained using an image containing that modified object. OVERVIEW

[0002] The invention is defined by the claims. To illustrate the invention, aspects and embodiments are described herein, which may or may not be within the scope of the claims.

[0003] Approaches are presented herein for generating synthetic images with one or more augmentations that are realistically added to objects in the images while ensuring the preservation and integrity of semantic or contextual information within the image. A synthetic augmentation system can identify and extract foreground image data (e.g., text), and a version of the image with the foreground image data removed can be processed by a generative diffusion model. One or more inputs can be provided to specify aspects such as the type or strength of the augmentation to be performed. After an augmented image has been generated using the generative diffusion model, the previously removed text can be re-imposed into the image.A synthetic enhancement system can apply one or more blend weights to the text, such as a defect blend weight and a letter blend weight. The final result is an image with added realistic enhancements that preserves the semantic content.

[0004] The disclosure extends to any novel aspects or features described and / or illustrated herein.

[0005] Further features of the disclosure are characterized by the independent and dependent claims.

[0006] Any feature in one aspect of the disclosure may be applied to other aspects of the disclosure in any suitable combination. In particular, method aspects may be applied to device or system aspects, and vice versa.

[0007] Furthermore, features implemented in hardware may also be implemented in software, and vice versa. Any reference to software and hardware features in this description should be construed accordingly.

[0008] Any system or device feature described herein may also be provided as a method feature, and vice versa. Functionally described system and / or device aspects (including means-plus-function features) may alternatively be expressed in terms of their corresponding structure, such as a suitably programmed processor and associated memory.

[0009] It should also be understood that certain combinations of the various features described and defined in any aspects of the disclosure may be implemented and / or provided and / or used independently of one another.

[0010] This disclosure also provides computer programs and computer program products comprising software code adapted, when executed on a computing device, to perform any of the methods described herein and to embody device and system features, including any or all substeps of a method.

[0011] The disclosure also provides a computer or computing system (including networked or distributed systems) having an operating system that supports a computer program for performing any of the methods described herein and / or embodying any of the device or system features described herein.

[0012] The disclosure also provides a computer-readable medium having stored thereon one or more of the aforementioned computer programs.

[0013] The disclosure also provides a signal carrying one or more of the aforementioned computer programs.

[0014] The disclosure extends to methods and / or devices and / or systems as described herein with reference to the accompanying drawings.

[0015] Aspects and embodiments of the disclosure will now be described, by way of example only, with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Various embodiments in accordance with the present disclosure will be described with reference to the drawings, in which: Fig. 1A-1C illustrate synthetic images of a traffic sign, according to various embodiments; Fig. 2 illustrates an example system environment including a synthetic variation generation system, according to various embodiments; Fig. 3 illustrates an exemplary block diagram illustrating modules in the synthetic variation generation system, according to various embodiments; Fig. 4 illustrates an example block diagram illustrating modules in a pop-up module, according to various embodiments; Fig. 5 illustrates an example process for generating synthetic variations of an image, according to various embodiments; Fig. 6 illustrates an exemplary process for generating synthetic images, according to various embodiments; Fig. 7A illustrates inference and / or training logic, according to at least one embodiment; Fig. 7B illustrates inference and / or training logic, according to at least one embodiment; Fig. 8 illustrates an exemplary data center system, according to at least one embodiment; Fig. 9 illustrates a computer system, according to at least one embodiment; Fig. 10 illustrates a computer system according to at least one embodiment; Fig. 11 illustrates at least portions of a graphics processor, according to one or more embodiments; Fig. 12 illustrates at least portions of a graphics processor, according to one or more embodiments; Fig. 13 is an example dataflow diagram for an advanced compute pipeline, according to at least one embodiment; Fig. 14 is a system diagram for an example system for training, adapting, instantiating, and deploying machine learning models in an advanced computational pipeline, according to at least one embodiment; and Fig. 15A and Fig. 15B illustrate a dataflow diagram for a process for training a machine learning model and client-server architecture for enhancing annotation tools with pre-trained annotation models, according to at least one embodiment. DETAILED DESCRIPTION

[0017] In the following description, various embodiments are described. For purposes of explanation, specific configurations and details are set forth in order to provide a thorough understanding of the embodiments. However, one skilled in the art will recognize that the embodiments may be practiced without the specific details. Furthermore, well-known features may be omitted or simplified in order not to obscure the described embodiments.

[0018] The systems and methods described herein may be used by, among others, non-autonomous vehicles, semi-autonomous vehicles (e.g., in one or more Advanced Driver Assistance Systems (ADAS)), guided and unguided robots or robotic platforms, warehouse vehicles, off-road vehicles, vehicles coupled to one or more trailers, flying vehicles, boats, shuttle vehicles, emergency response vehicles, motorcycles, electric or motorized bicycles, aircraft, construction vehicles, trains, underwater vehicles, remotely operated vehicles such as drones, and / or other types of vehicles.Furthermore, the systems and methods described herein may be used for a variety of purposes, including, but not limited to, machine control, machine locomotion, machine propulsion, synthetic data generation, model training or updating, perception, augmented reality, virtual reality, mixed reality, robotics, security and surveillance, simulation and digital twinning, autonomous or semi-autonomous machine applications, deep learning, environmental simulation, object or actuator simulation and / or digital twinning, data center processing, conversational AI, light transport simulation (e.g., ray tracing, path tracing, etc.), collaborative content creation for 3D assets, cloud computing, and / or other suitable applications.

[0019] Disclosed embodiments may be included in a number of different systems, such as automotive systems (e.g., a control system for an autonomous or semi-autonomous machine, a perception system for an autonomous or semi-autonomous machine), systems implemented using a robot, antenna systems, media systems, boat systems, intelligent area monitoring systems, systems for performing deep learning operations, systems for performing simulation operations, systems for performing digital twinning operations, systems implemented using an edge device, systems incorporating one or more virtual machines (VMs), systems for performing synthetic data generation operations, systems implemented at least partially in a data center, systems for performing conversational AI operations,Systems for performing light transport simulation, systems for performing collaborative content creation for 3D assets, systems implemented at least in part using cloud computing resources, and / or other types of systems.

[0020] Approaches according to various illustrative embodiments provide synthetic modification of image content, including the ability to introduce realistic (or stylistic) modifications or enhancements—such as defects—into images that may themselves be synthetically generated. The synthetic modification may be performed in a manner that preserves any context or important aspects or features of objects represented in the image for which enhancement is to be performed, thereby ensuring the preservation and integrity of critical information within the image.For example, if the image is a traffic sign containing important text or content, a synthetic modification system may identify and extract that important text or content, such as using an optical character recognition (OCR) tool, and identify textual content and remove or extract the textual content from the image. The extraction or removal may result in an image of the subject without the identified textual content. The extraction process may partially fill the pixel locations of the removed text based on pixel values ​​for neighboring pixel locations to generate a version of the object that appears realistic but without the extracted text.This version of the object without the text can, for example, be used as input to a generative diffusion model, which can cause it to generate or synthesize a version of this image that has one or more specified enhancements added or applied to the object. Removing the text from the image with a generative (e.g., latent) diffusion model can prevent the model from generating unwanted transformations to the text, such as changing characters in the text as a result of the diffusion process. Alongside this image, at least one prompt can be provided as input to the diffusion model to inform one or more aspects of the enhancement to be performed, which can relate to the type and intensity of the enhancement. This can be a characteristic of a defect (e.g., rust) and its target severity (e.g.,ranging from lightly to heavily rusted). After the augmented sign image has been generated, with the rust augmentation added, the previously extracted text can be added back to or blended into the augmented image. A synthetic augmentation system may employ one or more weights for the integration process, such as a defect overlay weight and a text overlay weight, which can be used to determine final pixel values ​​for pixel locations corresponding to text, based in part on whether a defect (or other augmentation) is present at those locations. The final result may thus be a synthetic image with added realistic augmentations (such as defects) that preserves contextual (or other potentially essential) information or content within the image.

[0021] A synthetic augmentation system according to at least one embodiment may provide several technical advantages and improvements. For example, a synthetic augmentation system may utilize a uniquely structured neural network pipeline that includes a contextual (or foreground) data removal stage that ensures preservation of important information, such as text or other foreground elements, within images. Compared to existing techniques where a diffusion model may distort essential information in an image, a synthetic augmentation system may prevent at least some unintentional distortion or deletion of these critical details during the infusion of synthetic defects by extracting the essential information while applying the diffusion process.Furthermore, according to at least one embodiment, a synthetic enhancement system can introduce a high degree of realism to the synthetic defects, such as rust, ensuring that the synthetic defects are integrated with both textual (e.g., foreground) and non-textual (e.g., background) elements of the image. Traditional methods often encounter challenges in striking a balance between realism and maintaining image integrity. For example, common problems can include the inappropriate layering of text or other foreground elements on top of synthetic defects, such as rust, resulting in an unrealistic appearance. For example, if rust is added to a sign, but the text on the sign overlies the rust, the resulting image may contradict the natural pattern of rust, degrading all exposed surfaces.In contrast, a synthetic enhancement system can ensure that synthetic defects (or other enhancements) are uniformly integrated across the image, affecting both background and foreground elements. A synthetic enhancement system can create a realistic blend of the defect, such as rust, with all image components, including text. As a result, a synthetic enhancement system generates images in which synthetic defects appear to interact with all aspects of the image, mirroring the way these defects would appear in real-world conditions.

[0022] Furthermore, a synthetic augmentation system can efficiently address the problem of data sparsity when training deep learning models. Such a system can partially address this problem by generating diverse variations of individual images, where these variations can incorporate different types and levels of augmentation or synthetic modification. A synthetic augmentation system can therefore be used to increase the volume and variety of training data, thereby providing a larger and more diverse dataset for model training. A resulting benefit is the development of more robust models capable of effectively handling a wide variety of real-world imperfections.The synthetic augmentation system therefore offers significant improvements in the creation of realistic and diverse synthetic images while preserving crucial details, representing an advance over previous approaches.

[0023] Variations of this and other such functionality may also be used within the scope of the various embodiments, as one of ordinary skill in the art will recognize in light of the teachings and recommendations contained herein.

[0024] Fig. 1A-1C illustrate a set of images, including variations of an object, that can be generated using a synthetic image generation process. Fig. 1A illustrates a first image 100 including a base image representation of a traffic sign, including important contextual information, in this example including important text. Fig. The traffic sign displayed in Figure 1A includes two sections, with the upper section having white letters spelling out "TOW-AWAY" on a colored (e.g., red) background, and the lower section having colored (e.g., red) letters spelling out "SPECIAL PLACARD OR LICENSE PLATE REQUIRED" on a white background. To enhance a variety of realistic images, it may be desirable to add one or more enhancements to the sign in the image, such as adding real-world imperfections (e.g., rust) to the sign and potentially generating versions with varying degrees of those imperfections (e.g., different amounts of rust corresponding to different ages or conditions of the sign).

[0025] Fig. Figure 1B illustrates an exemplary synthetically modified image 110 that may be produced using a generative diffusion model. In this example, the base image 100 of Fig. 1A as input to a generative diffusion model, which may output the synthetically modified image 110, which may include specified enhancements, such as the introduction of rust into the sign. However, as illustrated, the synthetically modified image 110 also includes other changes to the sign that may not be desirable. While the goal was to introduce a realistic rust effect into the sign, the image output by the generative diffusion model also included undesirable distortions of the sign's textual content. For example, "TOW-AWAY" inadvertently mutated to "T0W-^W^Y," while "SPECIAL" was incorrectly rendered as "5PECIAL." The Fig. The syntax distortions of the text seen in Figure 1B may be introduced by a naive application of a diffusion process, potentially altering essential information that should remain (essentially and recognizably) unchanged. Alternatively, existing approaches may perform text removal and replacement to mitigate such distortions, but naively apply post-diffusion text replacement, producing text elements that do not blend realistically with the rust details. In a real-world context, the rust would affect all exposed surfaces, including the text. In the synthetically generated image 110 in Fig. 1B, however, the rust appears as a layer beneath the text, contributing to an unnatural, unrealistic appearance. Consequently, images such as Fig. 1B may not be ideal for operations such as training machine learning models, as they illustrate scenarios that would be unlikely to occur in the real world. Accurate real-world scenarios may be underrepresented in a training dataset.

[0026] Fig. 1C illustrates another exemplary synthetically augmented image 120 that may be generated in accordance with at least one embodiment. In this exemplary synthetically augmented image 120, the realistic augmentation appears to blend seamlessly with the base image 100 of Fig. 1A, while maintaining the integrity of essential details, such as the textual content of the sign. A synthetic augmentation system according to at least one embodiment may identify and extract contextual content, perform synthetic augmentation of the image without the contextual content, and then realistically overlay the extracted content back into the augmented image. Such an approach may create a harmonious visual effect, with the text realistically influenced (or otherwise modified) by the synthetic rust. The synthetically augmented image 120 of Fig. 1C therefore largely imitates natural and realistic changes to the basic image 100 of Fig. 1A with added rust or color changes caused by environmental factors such as air exposure and sunlight, without the unwanted contextual modifications seen in the synthetically modified image 110 of Fig. 1B, generated using a naive diffusion generation process. In at least one embodiment, the synthetic enhancement system may allow customization of the type and severity of such enhancements, which may be based on specific text prompts, style codes, or other such inputs. This may include a wide range of possible effects or enhancements, such as different types and amounts of speckles or dust, providing further flexibility in generating realistic synthetic images for different use cases.

[0027] Fig. Figure 2 illustrates an exemplary system including a synthetic augmentation system, according to at least one embodiment. As an example, Fig. 2 illustrates an exemplary networked system 200 that may be used to provide, generate, modify, encode, process, and / or transmit image data or other such content. The exemplary networked system 200 may include a client device 202, another client device 203, a network 214, a third-party service 260, and a provider environment 216 including a synthetic augmentation system 230.

[0028] Client device 202 may generate or receive data for a session using components of an application 207 on client device 202 and data stored locally on that client device 202. For example, a user may utilize client device 202 to generate synthetic images using application 207. This may include the generation of synthetically enhanced images, as discussed herein. Although only one client device 202 is illustrated in detail, example networked system 200 may include one or more other client devices 203 that may communicate with provider environment 216 via network 214.A client device 202 may be any suitable computing device capable of enabling a user to generate synthetic images as discussed herein, and may include, for example, a desktop computer, a notebook computer, a workstation, a gaming console, a set-top box, a streaming device, a smartphone, a tablet computer, a VR headset, AR glasses, a wearable computer, or a smart TV. In at least one embodiment, a user may generate synthetic variations using a user interface (UI) 206 running on a client device 202, although at least some functionality may also be operated on a remote device, networked device, or via a cloud computing platform.In at least one embodiment, a user may provide input to UI 206, such as via a touch-sensitive display 204 or by moving a mouse cursor displayed on a display screen. In one embodiment, a user may provide input, such as images and text prompts, to an application 207 for generating synthetic images, labels, training datasets, and control datasets. The application 207 may be provided by the provider environment 216 for the user to download to the client device 202. In at least one embodiment, a client device may include at least one processor 208 (e.g., a CPU or GPU) and memory 210 for executing the application 207 and / or performing tasks for the application 207. In at least one embodiment, synthetic images generated by the application 207 may be stored locally at a local storage 212.

[0029] In one embodiment, each client device 202 may send a request over at least one wired or wireless network, which may include the Internet, an Ethernet, a local area network (LAN), or a cellular network, among other such options. In this example, these requests may be sent to an address associated with a cloud provider that may operate or control one or more electronic resources in a cloud provider environment, which may include, for example, a data center or server farm. In at least one embodiment, the request may be received or processed by at least one edge server located at a network edge and external to at least one security layer associated with the cloud provider environment.In this way, latency can be reduced by allowing client devices to interact with servers located in close proximity, while improving the security of resources in the cloud provider environment.

[0030] Network 214 may represent the communication paths of client device 202, provider environment 216, other client device 203, and third-party service 260. Through network 214, client device 202 may send input information associated with synthetic image generation over network 214. The information may be received by a remote computing system that may be part of a resource provider environment 216. In one embodiment, network 214 is the Internet. Network 214 may include any suitable network, including an intranet, Internet, a cellular network, a local area network (LAN), or any other such network, or a combination, and communication over a network may be enabled via wired and / or wireless connections.Network 214 may also utilize dedicated or private communication links that are not necessarily part of the Internet. In one embodiment, network 214 utilizes standard communication technologies and / or protocols. Therefore, network 214 may include links employing technologies such as Ethernet, Wi-Fi, Integrated Services Digital Network (ISDN), Digital Subscriber Lines (DSL), Asynchronous Transfer Mode (ATM), etc. Likewise, network protocols employed on network 214 may include Multiprotocol Label Switching (MPLS), Transmission Control Protocol / Internet Protocol (TCP / IP), Hypertext Transport Protocol (HTTP), Simple Mail Transfer Protocol (SMTP), File Transfer Protocol (FTP), etc.In one embodiment, at least some of the links use mobile network technologies, such as Long Term Evolution (LTE). The data exchanged over network 214 may be represented using technologies or formats including Hypertext Markup Language (XML), Wireless Access Protocol (WAP), Short Message Service (SMS), etc. Furthermore, all or some of the links may be encrypted using conventional encryption technologies, such as Secure Sockets Layer (SSL), Secure HTTP, or virtual private networks (VPNs). In another embodiment, client device 202 may use custom and / or dedicated data communication technologies instead of or in addition to those described above.

[0031] The provider environment 216 may include any suitable components for receiving requests and returning information or performing actions in response to those requests. Fig. In the embodiment illustrated in Figure 2, the provider environment 216 may include an interface 218 and a server 220, which may include various components for performing the tasks associated with generating synthetic images. In at least one embodiment, the provider environment 216 may include web servers and / or application servers for receiving and processing requests, then returning data or other content or information in response to a request.

[0032] The interface 218 can receive communications to the server 220. In at least one embodiment, the interface layer 218 can include application programming interfaces (APIs) or other exposed interfaces that enable a user to send requests to the server 220. In at least one embodiment, the interface 218 can also include other components, such as at least one web server, routing components, or load balancers. In at least one embodiment, components of an interface layer 218 can determine a type of request or communication and can direct a request to an appropriate system or service, such as the synthetic extension system 230.

[0033] The server 220 may include a transmission manager 222, a content application 224, an object repository 234, and a user database 236. The server 220 may receive requests and data from the client device 202, perform tasks associated with the requests, and send results or other data to the client device 202. In at least one embodiment, a content application 224 executing on the server 220 (e.g., a cloud server or edge server) may initiate a session associated with the client device 202 using a session manager and user data stored in a user database 236, and may cause content, such as one or more object representations—such as images—to be selected from an object repository 234 by a content manager 226 for processing.At least some of the generated content, such as synthetic images generated by the synthetic augmentation system 230, may be transmitted to the client device 202 using an appropriate transmission manager 222 for transmission via download, streaming, or other such transmission channel. An encoder may be used to encode and / or compress at least some of this data before transmitting it to the client device 202. In at least one embodiment, the client device 202 receiving such content may pass this content 207 to an appropriate application for selecting, delivering, synthesizing, modifying, or using the content for presentation (or other purposes) on or by the client device 202.A decoder may also be used to decode data received over the network(s) 214 for presentation via the client device 202, such as image or video content through a touch-sensitive display 204. In at least one embodiment, at least a portion of the content may already be stored, rendered, or accessible on the client device 202, such that transmission over the network 214 is not required for at least that portion of the content, for example, where the content may have been previously downloaded or stored locally on a hard drive or optical disk. In at least one embodiment, a transmission mechanism, such as data streaming, may be used to transfer the content from the server 220, or the user database 236, to the client device 202.In at least one embodiment, a portion of this content may be obtained, enhanced, and / or streamed from another source, such as a third-party service 260 or another client device 203, which may also include a content application 262 for generating, enhancing, or delivering content. In at least one embodiment, portions of this functionality may be performed using multiple computing devices, or multiple processors within one or more computing devices, which may include, for example, a combination of CPUs and GPUs.

[0034] In at least one embodiment, server 220 may include a processor, such as a central processing unit (CPU). However, in at least one embodiment, resources in such environments may utilize GPUs to process data for at least certain types of requests. In at least one embodiment, with thousands of cores, GPUs are designed to handle significant parallel workloads and have therefore become popular in deep learning for training neural networks and generating predictions.While the use of GPUs for offline builds has enabled faster training of larger and more complex models, in at least one embodiment, generating predictions offline implies that either request-time-input features cannot be used or predictions for all permutations of features must be generated and stored in a lookup table to serve real-time requests. Then, in at least one embodiment, if a deep learning framework supports a CPU mode and a model is small and simple enough to perform feedforward on a CPU with reasonable latency, a service on a CPU instance could host a model. In at least one embodiment, training can be done offline on a GPU and inference can be done in real time on a CPU.In at least one embodiment, if a CPU approach is not a viable option, a service may run on a GPU instance. However, in at least one embodiment, because GPUs have different performance and cost characteristics than CPUs, a service that offloads a runtime algorithm to a GPU may require that it be designed differently than a CPU-based service.

[0035] The server 220 may include a content application 224 that includes a content manager 226 and a synthetic augmentation system 230. As previously discussed, the content manager 226 may send objects, such as images, from the object repository 234, along with requests and other data from the client device 202, to the synthetic augmentation system 230 for generating synthetic images. The synthetic augmentation system 230 may generate synthetic images with variations, such as defects, and may provide the results to the transmission manager 222 for sending back to the client device 202. The synthetic augmentation system 230 may also use local datasets or datasets provided by the third-party service 260 to train machine learning models that can generate synthetic images and store the trained models in a model repository.The functionality associated with the synthetic extension system 230 is described in greater detail in accordance with . Fig. 3 discussed.

[0036] Fig. 3 illustrates components of an exemplary synthetic augmentation system 230, according to at least one embodiment. A synthetic augmentation system 230 may include a foreground identification and extraction module 302 that can identify "foreground" content of an image, such as text, characters, symbols, or other contextual elements that need to be preserved during an augmentation or modification process. The foreground identification and extraction module 302 may include an OCR component that can identify pixels corresponding to text and an extraction component for "removing" the text from the image by modifying the pixel values ​​for the pixel locations of the text based on values ​​of neighboring pixels to cause the image to appear as if the text was not present in the image, but otherwise retaining the appearance of the object.The "removed" text—which may include pixel values ​​for pixel locations corresponding to the identified text—may be stored in a foreground data repository, such as a cache or other temporary storage. The synthetic augmentation system 230 also includes a trained generative diffusion model 304 that may take the image (with foreground removed) as input and generate a synthetic image (or image data) having one or more augmentations added to or otherwise present in the image. The synthetic augmentation system also includes an overlay module 306 that overlays the removed foreground data from the temporary storage 308 back into the image, including the augmentations, using one or more overlay weights determined by the overlay module 306.If the augmentation system also performs training, then the system may include a training data repository 324 and may store the augmented image 322 as training data for use in training a model selected from a model repository 326 that stores untrained and / or trained models in at least one embodiment.

[0037] A synthetic enhancement system 230 may operate by receiving a request to generate synthetic variations or enhancements for an input image 310. This input image may include a foreground portion, such as (for example and without limitation): text, textual information, sticker-like overlays, graphic overlays, graphic symbols, icons, characters, letters, etc., and a background portion. The synthetic enhancement system 230 may separate the foreground information, or other details that need to be preserved, from the image. The isolated background image data may then be processed through a diffusion model 304, which introduces variations or enhancements (e.g., defects) into the image.The enhancements may be specified by one or more instances of an enhancement input 312, which may take the form of a text prompt, a voice input, a style code, or other such input. The enhancement input may specify one or more types of enhancements to be added or generated, such as rust, dust, graffiti, rot, mold, or other damage, and the like, as well as an amount, extent, or strength of the enhancement, where a strength of 0 for a rust enhancement may indicate that no rust is to be added, and a strength of 1 for a rust enhancement may indicate that the sign appears completely rusted, with values ​​between 0 and 1 indicating relative amounts of rust. An image generated according to the enhancement input 312 may have its foreground reintroduced.As mentioned, a blending module 306 may calculate a character blending weight (or other content blending weight) and a defect blending weight (or other enhancement blending weight), which may be used to determine how to blend the previously removed foreground information back into the enhanced image 322. The blending module 306 may ensure that the reintroduced foreground is harmoniously incorporated, influenced by the added defects, while maintaining the original semantics. Each module in the synthetic enhancement system 230 is discussed in more detail in the following sections.

[0038] In at least one embodiment, a foreground identification and extraction module 302 may detect and extract pixel values ​​corresponding to foreground information from an input image. Foreground information, as used herein, may refer to elements in an image, where the elements have semantic or contextual meaning that may be desired to remain unchanged during a synthetic augmentation process. In other words, despite the introduction of variations or modifications, the inherent meaning, expression, or value of these foreground elements must be consistently maintained. In at least one embodiment, the foreground may range from textual information, such as letters on a sign, to visual data, such as stickers, or symbols, such as wheelchair accessibility symbols, arrows, or pedestrian crossing signs.To isolate the textual information, the foreground identification and extraction module 302 may apply OCR (optical character recognition) or other content identification models, algorithms, or processes that allow the module to detect and identify text present in the input image, or at least text that is determined to be likely to be meaningful based on factors such as size or location in the image. For non-textual elements, such as decals or symbols, the module may use pattern recognition techniques or machine learning algorithms trained to detect specific shapes or symbols. Once the necessary foreground information has been identified, the foreground identification and extraction module 302 may proceed to extract the identified foreground information from the original input image.The foreground identification and extraction module 302 may generate a companion image or mask consisting exclusively of the removed foreground information. For example, if the input image is a sign with text, the foreground identification and extraction module 302 may generate a pixel image retaining only the pixels corresponding to the textual information. The foreground identification and extraction module 302 may use OCR models to identify areas containing text, extract foreground data corresponding to an image mask of the pixels corresponding to the identified foreground data, and store the extracted foreground data as a new image or a new mask with pixels corresponding to the foreground. This mask may later be reintegrated with the background image processed by the diffusion model 304.The foreground identification and extraction module 302 may generate another image with the foreground information removed, resulting in an image with only the background information for the diffusion process.

[0039] A generative diffusion model 304 (or another suitable generative model, network, or process) can process variations or extensions after foreground removal and add them to the image, keeping it focused on the background or other portions of the image. The background of the image, as used herein, can refer to the image after foreground removal or pixel locations corresponding to a specific object in the image after foreground removal. For example, if rust is to be applied to a sign in an image, the diffusion model would be sufficiently trained to apply rust only to the sign and not to bushes, grass, sky, or other background objects that may also be present in an image "background."The diffusion model 304 introduces realistic variations or defects into the image, such as rust or wear, simulating natural environmental effects on the image object. The diffusion model 304 may be a generative model, such as an image-to-image diffusion model. Image-to-image diffusion models operate by taking an input image and denoising it according to the model parameters, thereby producing images that contain more variety (i.e., smart noise). In one or more embodiments, the diffusion model 304 may take the image from which the foreground has been removed as input. The diffusion model 304 may take additional inputs, such as textual prompts, that provide guidance regarding the nature and intensity of the defect (noise) to be introduced.The prompts may, for example, specify, among other things, "light rusting," "heavy rusting," "five years of sun exposure," etc. The diffusion model 304 may start with the input image and progressively (intelligently) add noise to it through a sequence of steps. The diffusion model 304 may progressively refine this noisy data into an image through iterative steps. Each refinement iteration may aim to reduce the noise and increase the quality of the image to result in a realistic image of one or more objects of the types or classes for which the model has been trained. Each refinement step may aim to predict the noise added during the corresponding step in the forward process.This can be achieved by training a neural network to estimate the conditional distribution of the original data with the given noisy data at each step. The model gradually refines the noisy data back into an image over a series of steps, with the goal of reducing the noise and restoring the image before the noise addition stage.

[0040] In one embodiment, diffusion model 304 also adjusts the degree and characteristics of the variations introduced into the image. For example, the intensity of the changes can be controlled, and diffusion model 304 can simulate effects with varying degrees of severity, such as the minor changes produced by five years of rust versus the effects of a hundred years of corrosion. The content of the graffiti or the type of lighting conditions can also be controlled using text prompts. Furthermore, diffusion model 304 can adjust the nature of the variations in response to the specified prompts. These prompts can be used to specify a wide range of potential modifications.This includes environmental influences such as dust, rust, rain, and fog; adding contextual elements such as objects that may appear on the road, such as pedestrians or a pedestrian crossing; adjusting the ambience of the image by modifying lighting and shadows; and generating defects such as cracks or scratches. The diffusion model 304 may also be guided to include elements such as graffiti based on text prompts. The output image from the diffusion model 304 is a modified image incorporating the requested variations, such as defects. This modified image may also be referred to as a diffusion image for convenience in the following discussions. Once generated, the diffusion image is then provided to the overlay module 306 for further processing, whereupon, according to Fig. 4 will be discussed in more detail.

[0041] The overlay module 306 can re-overlay the previously removed foreground information into the extended image 322. Exemplary components of such an overlay module 306 are described in Fig. 4. A blending module 306 may include a dominant color finder 404 that identifies dominant colors and a blending weight determination module 406 that determines parameters related to the blending process. Since the stable diffusion process often results in a series of color variations around an area that originally had a single color in the input image, the blending module 306 may decide on one or more dominant colors in the diffusion image. After the dominant colors are identified, the blending module 306 may use the dominant colors to determine how to combine the elements of the image, such as the foreground, characters, background, and defects. In one embodiment, the blending module 306 may determine an appropriate mix of the variations (e.g., defects) and the foreground (e.g.,Text) based on how much each pixel behind the foreground deviates from the dominant color. For example, consider a scenario where the background of a sign is red and the letters are white. If a particular pixel behind the text is closer in color to the dominant red color, the system will blend more of the white letter into that pixel. If a pixel deviates significantly from the center red color (perhaps due to the presence of a rust defect), blending module 306 will assign more weight to the defect. The functionality associated with each of modules 404 and 406 is discussed in further detail below.

[0042] The dominant color finder 404 can identify dominant colors in an image. An image output from the diffusion model 304 can include complex colors when variations are added. For example, consider a traffic sign that originally displayed only red and white colors. After being processed by the diffusion model 304, the sign may now display a variety of shades within the red and white color spectrum, perhaps including shades of orange and brown to simulate the effect of rust. The dominant color finder 404 can analyze the image and determine one or more dominant colors. The dominant color finder 404 can include a color analysis module 410 and a color clustering module 412.

[0043] The color analysis module 410 may perform a spectrum analysis of colors. The color analysis module 410 may use a hyperparameter that specifies the number of most frequently occurring colors in the original image. The color analysis module 410 may find a number of the most frequently occurring colors based on the hyperparameter. For example, in the scenario of a stop sign that was originally red and white, the diffusion image may display different shades of red and white after being processed by the diffusion model 304. If the hyperparameter that specifies the number of most frequently occurring colors in the image is set to 30, the color analysis module 410 may categorize all unique RGB colors present in the image and select the 30 most predominant ones.In this specific example, the color analysis module 410 will likely identify numerous variations of red and white, as these are the dominant colors in the image. The identified tones will largely be closely associated with red or white, but may have a wide range of hue variations. The color variations identified by the color analysis module 410 may be passed to the color clustering module 412 for further processing.

[0044] The color clustering module 412 groups the colors identified by the color analysis module 410. In one embodiment, the color clustering module 412 may use a machine learning or clustering algorithm to group the colors identified by the color analysis module 410 into clusters. The color clustering module 412 may calculate a mean color based on the values ​​in a cluster, and the mean color may be considered the dominant color. In one embodiment, the mean color is calculated by averaging the individual red, green, and blue (RGB) color component values ​​at all pixels in the cluster. For each pixel in the cluster, the RGB values ​​are summed separately, and the sums are then divided by the total number of pixels in the cluster, resulting in three mean values ​​corresponding to each of the RGB components.This resulting mean color represents the “average color” of all pixels within that specific cluster.

[0045] The color clustering module 412 may further use a parameter (e.g., M) to specify the maximum number of dominant colors. This parameter M guides the process by setting a limit on the most frequently occurring colors to be considered when identifying the dominant colors. For example, in the case of a stop sign with white text on a red background, it should be noted that the parameter M may be set to 2, indicating that two dominant colors may be specific shades of white and red. In one embodiment, the color clustering module 412 trains and uses a clustering model that accepts the number of desired clusters as input, thereby matching the number of clusters to the maximum number of most frequently occurring colors. This results in the formation of color groups that are consistent with the primary colors present in the image.In one embodiment, the color clustering module 412 may employ a clustering model that optimizes itself autonomously and is not limited to a prespecified number of clusters. In this situation, the color clustering module 412 would focus on the largest M clusters of those formed to determine the dominant colors. In the case of a stop sign as an illustrative example, the color clustering module 412 may be instructed to set a maximum number of the most frequently occurring colors as 2 (e.g., M = 2). The color clustering module 412 receives the 30 most predominant colors in the diffusion image from the color analysis module and proceeds to classify these colors into distinct groups. From these groupings, the color clustering module 412 may identify the two largest clusters. In this specific example of a stop sign, the two clusters may include various shades of red and white.The color clustering module 412 then determines the mean color for each of these two clusters and the mean colors are then designated as the dominant colors for the image.

[0046] The blend weight determination module 406 may determine parameters for blending the foreground and variations back into the image, such as by using a blend implementation module 408, to produce a final synthetic image with generated variations. In one embodiment, the blend weight determination module 406 determines a letter blend weight and a defect blend weight to determine the degree of blending of letters and defects for a pixel. The letter blend weight may determine the degree of blending of foreground elements, which may include, but are not limited to, textual information. Despite the term "letter," the blend weight may be applicable to any form of foreground detail to be blended back into the image. The defect blend weight determines the intensity of blending for variations or synthetically induced effects, such as defects.Despite the term "defect," this weight can be used to blend in any variations or effects desired to be included in the image. The blend weight determination module 406 can then use the letter blend weight and the defect blend weight to blend the foreground back into the image. In one embodiment, the blending process occurs on a pixel-by-pixel basis. For each individual pixel that is part of the foreground elements, such as text or symbols, the corresponding blend weights are derived from the matching pixel in the diffused or altered image. In other words, the blend weights are determined based on the characteristics of the pixel of the diffused image that would cover the foreground pixel.In situations where the pixel in the diffusion image deviates significantly from the dominant color, it can be concluded that the pixel in question has been severely affected by defects. As a result, a higher value is assigned to the defect fade-in weight. Conversely, if the pixel in the diffusion image clearly reflects the dominant color, this is a sign that the pixel has not been significantly altered, resulting in a higher value being assigned to the character fade-in weight.

[0047] In at least one embodiment, a blend weight determination module 406 may determine the weights using a threshold. In one embodiment, the deviation is quantified by an algorithm that uses a distance measure in color space. The distance measure may be a Euclidean distance, a Manhattan distance, or another relevant distance measure in color space. If the calculated deviation for a pixel exceeds the threshold, the blend weight determination module 406 may determine that the pixel is severely affected by defects and is therefore assigned a higher defect blend weight. If the deviation is below the threshold, it indicates that the pixel is closer to the dominant color and is therefore assigned a higher letter blend weight. In another embodiment, the blend weight determination module 406 may use a function of the deviation to determine the weights.For example, the defect fade weight may be an increasing function of deviation (e.g., linear or exponential), and the letter fade weight may be a decreasing function of deviation. In one embodiment, machine learning techniques may be used to determine the fade weights. A model may be trained to predict the weights based on the deviation, perhaps taking into account other features such as the spatial location of the pixel, the color distribution in the pixel's neighborhood, etc.

[0048] Fig. Figure 5 illustrates an example process flow including example image illustrations for creating a synthetic image with added variations. In Fig. 5, image 510, which includes a representation of a traffic sign divided into two sections, is the input image. The upper section features the letters "TOW-AWAY" on a red background, and the lower section features the letters "SPECIAL PLACARD OR LICENSE PLATE REQUIRED" on a white background. The goal is to introduce rust effects into the traffic sign shown in image 510.

[0049] Foreground identification and extraction 302 may first perform a foreground removal process 511 by extracting the foreground, such as text, from image 510. Two instances of image data are produced by foreground removal process 511, including an image 520 corresponding to the background image data with the text removed, and image data 530 corresponding to the "removed" pixel values ​​corresponding to the extracted text. After foreground removal process 511, background image 520 is subjected to an augmentation process 512 by being passed as input to a diffusion model 304. Given text prompts and a background image 520, diffusion model 304 may, for example, produce an augmented image 540 in which background image 520 now has defects embedded therein.While the original input field 510 may only have a flat red and a flat white, the augmented image 540 may have various shades and tones of red and white, along with colors associated with rust, such as brown and orange.

[0050] A blending module 306 may then perform a blending process 513 that includes the extracted foreground image data 530 and the augmented image data 540. A dominant color finder 404 of the blending module 306 may determine dominant colors in the augmented image 540. Since the augmented image 540 may have a complicated color scheme due to the defect generation process, the dominant color finder 404 may first determine a number of the most frequently occurring colors and clusters of the colors. The dominant colors are determined by averaging the colors in each cluster. In this specific example, the number of dominant colors may be set to two, and the two dominant colors may be red and white. To determine how to blend each pixel from the foreground image 530 into the final image, the blending weight determination module 406 determines a character blending weight and a defect blending weight.These weights specify how each pixel from the foreground image 530 should be blended with the augmented image 540. If a pixel in the augmented image 540 matches the position of a pixel in the foreground image 530, the blending module 306 determines the weights based on the deviation of the pixel color in the augmented image 540 from the dominant color. A final image 550 is produced by blending the text back into the augmented image 540.

[0051] Fig. 6 illustrates an exemplary process 600 for generating a synthetic image with one or more augmentations, which may be performed in accordance with at least one embodiment. It should be understood that, within the scope of the various embodiments, there may be additional, fewer, or alternative steps for this and other processes herein, performed in similar or alternative orders, or at least partially in parallel. Furthermore, although described with respect to text, it should be understood that other contextual, semantic, or important elements may be removed and re-imposed on objects or regions of an augmented image unless specifically stated otherwise. In this example, an image 610 is obtained that includes at least a representation of an object for which augmentation is to be performed.Text (or other semantic or contextual content or elements) may be identified 620 and removed from the image, such as by modifying pixels corresponding to those pixel locations and storing the pixel values ​​for the removed content, as described herein. The image of the object, without the removed text or content, may be provided as input 630 to a generative diffusion model. An augmented image of the object may be received 640 as output of the generative diffusion model that includes one or more extensions added to the object. The removed text may then be blended back into the object in the augmented image using one or more blend weights 650 to allow realistic blending in both regions with and without added extensions or other image variations.The augmented image, including the representation of the object with the text that was present in the input image and the one or more realistically applied augmentations, may then be provided as output 660, such as for representation in a game or animation, or for use as training data, among other such options. INFERENCE AND TRAINING LOGIC

[0052] Fig. 7A illustrates inference and / or training logic 715 used to perform inference and / or training operations associated with one or more embodiments. Details regarding the inference and / or training logic 715 are described below in connection with Fig. 7A and / or 7B provided.

[0053] In at least one embodiment, the inference and / or training logic 715 may include, among other things, code and / or data storage 701 to store feedforward and / or output weights and / or input / output data and / or other parameters for configuring neurons or layers of a neural network being trained and / or used for inference in aspects of one or more embodiments. In at least one embodiment, the training logic 715 may include or be coupled to code and / or data storage 701 to store graph code or other software for controlling the timing and / or order in which weight and / or other parameter information for configuring logic, including integer and / or floating-point units (collectively, arithmetic logic units (ALUs)), is loaded.In at least one embodiment, code, such as graph code, loads weight or other parameter information into processor ALUs based on a neural network architecture to which the code conforms. In at least one embodiment, code and / or data storage 701 stores weight parameters and / or input / output data from each layer of a neural network trained or used in connection with one or more embodiments during forward propagation of input / output data and / or weight parameters during training and / or inference using aspects of one or more embodiments. In at least one embodiment, any portion of code and / or data storage 701 may be included with other on-chip or off-chip data storage, including processor L1, L2, or L3 cache or system memory.

[0054] In at least one embodiment, any portion of code and / or data storage 701 may be internal or external to one or more processors or other hardware logic devices or circuits. In at least one embodiment, code and / or data storage 701 may be cache memory, dynamic randomly addressable memory ("DRAM"), static randomly addressable memory ("SRAM"), non-volatile memory (e.g., flash memory), or other storage.In at least one embodiment, the choice of whether the code and / or data storage 701 is, for example, internal or external to a processor or consists of DRAM, SRAM, flash, or other storage type may depend on the available on-chip versus off-chip storage, the latency requirements of training and / or inference functions performed, the batch size of data used in inferring and / or training a neural network, or a combination of these factors.

[0055] In at least one embodiment, the inference and / or training logic 715 may include, among other things, code and / or data storage 705 to store backward and / or output weights and / or input / output data corresponding to neurons or layers of a neural network trained and / or used for inference in aspects of one or more embodiments. In at least one embodiment, the code and / or data storage 705 stores weight parameters and / or input / output data from each layer of a neural network trained or used in connection with one or more embodiments during backpropagation of input / output data and / or weight parameters during training and / or inference using aspects of one or more embodiments.In at least one embodiment, the training logic 715 may include or be coupled to code and / or data storage 705 for storing graph code or other software for controlling the timing and / or order in which weight and / or other parameter information is loaded to configure logic, including integer and / or floating-point units (collectively, arithmetic logic units (ALUs). In at least one embodiment, code such as graph code loads weight or other parameter information into processor ALUs based on a neural network architecture to which the code conforms. In at least one embodiment, any portion of the code and / or data storage 705 may be included with other on-chip or off-chip data storage, including processor L1, L2, or L3 cache or system memory.In at least one embodiment, any portion of the code and / or data storage 705 may be internal or external to one or more processors or other hardware logic devices or circuits. In at least one embodiment, the code and / or data storage 705 may be cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, the choice of whether the code and / or data storage 705 is, for example, internal or external to a processor or consists of DRAM, SRAM, flash, or other storage type may depend on the available on-chip versus off-chip storage, the latency requirements of training and / or inference functions performed, the batch size of data used in inferring and / or training a neural network, or a combination of these factors.

[0056] In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be separate storage structures. In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be the same storage structure. In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be partially the same storage structure and partially separate storage structures. In at least one embodiment, any portion of code and / or data storage 701 and code and / or data storage 705 may be included with other on-chip or off-chip data storage, including processor L1, L2, or L3 cache or system memory.

[0057] In at least one embodiment, the inference and / or training logic 715 may include, among other things, one or more arithmetic logic unit(s) ("ALU(s)") 710, including integer and / or floating-point units, for performing logical and / or mathematical operations based at least in part on or specified by training and / or inference code (e.g., graph code), a result of which may produce activations (e.g., output values ​​of layers or neurons within a neural network) stored in an activation storage 720 that are functions of input / output and / or weight parameter data stored in the code and / or data storage 701 and / or the code and / or data storage 705.In at least one embodiment, activations stored in activation storage 720 are generated according to linear algebraic and / or matrix-based mathematics performed by ALU(s) 710 in response to the execution of instructions or other code, using weight values ​​stored in code and / or data storage 701 and / or code and / or data storage 705 as operands along with other values, such as bias values, gradient information, momentum values, or other parameters or hyperparameters, any or all of which may be stored in code and / or data storage 701 or code and / or data storage 705 or other on- or off-chip storage.

[0058] In at least one embodiment, ALU(s) 710 are included within one or more processors or other hardware logic devices or circuits, while in another embodiment, ALU(s) 710 may be external to a processor or other hardware logic device or circuitry utilizing them (e.g., a coprocessor). In at least one embodiment, ALU(s) 710 may be included within execution units of a processor or otherwise within a series of ALUs accessible by execution units of a processor, either within the same processor or distributed among different processors of different types (e.g., central processing units, graphics processing units, fixed function units, etc.).In at least one embodiment, code and / or data storage 701, code and / or data storage 705, and enable storage 720 may reside on the same processor or other hardware logic device or circuit, while in another embodiment, they may reside on different processors or other hardware logic devices or circuits, or a combination of the same and different processors or other hardware logic devices or circuits. In at least one embodiment, any portion of enable storage 720 may be included with other on-chip or off-chip data storage, including processor L1, L2, or L3 cache or system memory.Furthermore, inference and / or training code may be stored with other code accessible to a processor or other hardware logic or circuitry, and may be retrieved and / or processed using fetch, decode, scheduling, execution, idle, and / or other logic circuitry of a processor.

[0059] In at least one embodiment, the activation storage 720 may be a cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, the activation storage 720 may be located entirely or partially within or external to one or more processors or other logic circuits. In at least one embodiment, the choice of whether the activation storage 720 is, for example, internal or external to a processor, or consists of DRAM, SRAM, flash, or another storage type, may depend on the available on-chip versus off-chip storage, the latency requirements of performed training and / or inference functions, the batch size of data used in inferring and / or training a neural network, or a combination of these factors. In at least one embodiment, the Fig. 7A may be used in conjunction with an application-specific integrated circuit (“ASIC”), such as a Tensorflow® Processing Unit from Google, an Inference Processing Unit (IPU) from Graphcore™, or a Nervana® processor (e.g., “Lake-Crest” processor) from Intel Corp. In at least one embodiment, the inference and / or training logic 715 illustrated in Fig. 7A may be used in conjunction with central processing unit (“CPU” hardware), graphics processing unit (“GPU” hardware), or other hardware, such as field programmable gate arrays (“FPGAs”).

[0060] Fig. 7B illustrates inference and / or training logic 715, according to at least one or more embodiments. In at least one embodiment, the inference and / or training logic 715 may include, among other things, hardware logic in which computational resources are dedicated or otherwise used exclusively in connection with weight values ​​or other information corresponding to one or more layers of neurons within a neural network. In at least one embodiment, the inference and / or training logic 715 may Fig. 7B may be used in conjunction with an application-specific integrated circuit (“ASIC”), such as a Tensorflow® Processing Unit from Google, an Inference Processing Unit (IPU) from Graphcore™, or a Nervana® processor (e.g., “Lake-Crest” processor) from Intel Corp. In at least one embodiment, the inference and / or training logic 715 illustrated in Fig. 7B may be used in conjunction with central processing unit (“CPU”) hardware, graphics processing unit (“GPU”) hardware, or other hardware, such as field programmable gate arrays (“FPGAs”). In at least one embodiment, the inference and / or training logic 715 includes, among other things, code and / or data storage 701 and code and / or data storage 705, which may be used to store code (e.g., graph code), weight values, and / or other information, including bias values, gradient information, momentum values, and / or other parameter or hyperparameter information. In at least one embodiment Fig. 7B, code and / or data storage 701 and code and / or data storage 705 are each associated with a dedicated computing resource, such as computing hardware 702 and computing hardware 706, respectively. In at least one embodiment, computing hardware 702 and computing hardware 706 each include one or more ALUs that perform mathematical functions, such as linear algebraic functions, only on information stored in code and / or data storage 701 and code and / or data storage 705, respectively, the results of which are stored in activation storage 720.

[0061] In at least one embodiment, the code and / or data storage 701 and / or data storage 701 and the corresponding computing hardware 702 and 706 correspond to different layers of a neural network, such that a resulting activation from a "storage / computing pair 701 / 702" of the code and / or data storage 701 and computing hardware 702 is provided as input to a "storage / computing pair 705 / 706" of the code and / or data storage 705 and computing hardware 706 to mirror the conceptual organization of a neural network. In at least one embodiment, each of the storage / computing pairs 701 / 702 and 705 / 706 may correspond to more than one neural network layer. In at least one embodiment, additional storage / computing pairs (not shown) may be included after or in parallel with storage / computing pairs 701 / 702 and 705 / 706 in the inference and / or training logic 715. DATA CENTER

[0062] Fig. Figure 8 illustrates an exemplary data center 800 in which at least one embodiment may be used. In at least one embodiment, the data center 800 includes a data center infrastructure layer 810, a framework layer 820, a software layer 830, and an application layer 840.

[0063] In at least one embodiment, as in Fig. 8, the data center infrastructure layer 810 includes a resource orchestrator 812, clustered compute resources 814, and node compute resources ("node CRs") 816(1)-816(N), where "N" represents a positive integer. In at least one embodiment, node CRs 816(1)-816(N) may include, among other things, any number of central processing units (CPUs) or other processors (including accelerators, field programmable gate arrays (FPGAs), graphics processors, etc.), memory devices (e.g., dynamic read-only memories), storage devices (e.g., solid-state or disk drives), network input / output (NW I / O) devices, network switches, virtual machines (VMs), power modules, and cooling modules, etc. In at least one embodiment, one or more of the node CRs 816(1)-816(N) may be a server having one or more of the computing resources mentioned above.

[0064] In at least one embodiment, grouped computing resources 814 may include separate groupings of node CRs housed in one or more racks (not shown) or multiple racks housed in data centers at different geographical locations (also not shown). Separate groupings of node CRs within grouped computing resources 814 may include grouped computing, networking, memory, or storage resources configured or allocated to support one or more workloads. In at least one embodiment, multiple node CRs, including CPUs or processors, may be grouped in one or more racks to provide computing resources to support one or more workloads.In at least one embodiment, one or more racks may also include any number of power modules, cooling modules, and network switches in any combination.

[0065] In at least one embodiment, resource orchestrator 812 may configure or otherwise control one or more node CRs 816(1)-816(N) and / or grouped computing resources 814. In at least one embodiment, resource orchestrator 812 may include a software design infrastructure (SDI) management entity for data center 800. In at least one embodiment, resource orchestrator 812 may include hardware, software, or a combination thereof.

[0066] In at least one embodiment, as in Fig. 8, a framework layer 820 includes a job scheduler 822, a configuration manager 824, a resource manager 826, and a distributed file system 828. In at least one embodiment, the framework layer 820 may include a framework to support software 832 of the software layer 830 and / or one or more applications 842 of the application layer 840. In at least one embodiment, the software 832 or application(s) 842 may each include web-based service software or applications, such as those provided by Amazon Web Services, Google Cloud, and Microsoft Azure. In at least one embodiment, the framework layer 820 may be, among other things, a type of free and open-source software web application framework, such as Apache Spark™ (hereinafter "Spark"), which may utilize the distributed file system 828 for large-scale data processing (e.g., "big data").In at least one embodiment, job scheduler 822 may include a Spark driver to facilitate scheduling workloads supported by various layers of data center 800. In at least one embodiment, configuration manager 824 may be capable of configuring various layers, such as software layer 830 and framework layer 820, including Spark and distributed file system 828, to support large-scale computing. In at least one embodiment, resource manager 826 may be capable of managing clustered or grouped computing resources allocated or allocated to support distributed file system 828 and job scheduler 822. In at least one embodiment, the clustered or grouped computing resources may include a clustered computing resource 814 at data center infrastructure layer 810.In at least one embodiment, the resource manager 826 may coordinate with the resource orchestrator 812 to manage these allocated or assigned computing resources.

[0067] In at least one embodiment, software 832 included in software layer 830 may include software used by at least portions of node CRs 816(1)-816(N), clustered computing resources 814, and / or distributed file system 828 of framework layer 820. The one or more types of software may include, among others, internet website search software, email virus scanning software, database software, and streaming video content software.

[0068] In at least one embodiment, application(s) 842 included in application layer 840 may include one or more types of applications used by at least portions of node CRs 816(1)-816(N), clustered computing resources 814, and / or distributed file system 828 of framework layer 820. One or more types of applications may include, but are not limited to, any number of genomics applications, cognitive computing applications, and machine learning applications, including training or inference software, machine learning framework software (e.g., PyTorch, TensorFlow, Caffe, etc.), or other machine learning applications used in connection with one or more embodiments.

[0069] In at least one embodiment, any of the configuration manager 824, resource manager 826, and resource orchestrator 812 may implement any number and type of self-modifying operations based on any amount and type of data collected in any technically feasible manner. In at least one embodiment, self-modifying operations may offload a data center operator of the data center 800 from potentially making poor configuration decisions and potentially avoiding underutilized and / or poorly performing portions of a data center.

[0070] In at least one embodiment, data center 800 may include tools, services, software, and other resources to train one or more machine learning models or to predict or infer information using one or more machine learning models according to one or more embodiments described herein. For example, in at least one embodiment, a machine learning model may be trained by calculating weight parameters according to a neural network architecture using software and computational resources as described above with respect to data center 800.In at least one embodiment, trained machine learning models corresponding to one or more neural networks may be used to derive and predict information using the resources described above relating to the data center 800 using weight parameters calculated via one or more training techniques described herein.

[0071] In at least one embodiment, the data center may use CPUs, application-specific integrated circuits (ASICs), GPUs, FPGAs, or other hardware to perform training and / or inference using the resources described above. Furthermore, one or more of the software and / or hardware resources described above may be configured as a service to allow users to train or perform information inference, such as image recognition, speech recognition, or other artificial intelligence services.

[0072] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. In at least one embodiment, the inference and / or training logic 715 may be implemented in the system of Fig. 8 for inferring or predicting operations based at least in part on weight parameters computed using neural network training operations, neural network functions and / or architectures, or neural network use cases as described herein.

[0073] Such components can be used to perform augmentation of an image using a generative diffusion model while retaining important contextual or semantic content. COMPUTER SYSTEMS

[0074] Fig. 9 is a block diagram illustrating an example computing system 900, which may be a system with interconnected devices and components, a system-on-a-chip (SOC), or other combination thereof, formed with a processor, which may include execution units for executing an instruction, according to at least one embodiment. In at least one embodiment, computing system 900 may include, among other things, a component, such as a processor 902, for employing execution units, including logic for performing algorithms on process data, in accordance with the present disclosure, such as in the embodiment described herein.In at least one embodiment, computing system 900 may include processors such as the PENTIUM® processor family, Xeon™, Itanium®, XScale™ and / or StrongARM™, Intel® Core™, or Intel® Nervana™ microprocessors available from Intel Corporation, Santa Clara, California, although other systems (including PCs with other microprocessors, engineering workstations, set-top boxes, and the like) may also be used. In at least one embodiment, computing system 900 may run a version of a WINDOWS operating system available from Microsoft Corporation, Redmond, Wash., although other operating systems (e.g., UNIX and Linux), embedded software, and / or graphical user interfaces may also be used.

[0075] Embodiments may be used in other devices, such as handheld devices and embedded applications. Some examples of handheld devices include cellular phones, Internet Protocol devices, digital cameras, personal digital assistants ("PDAs"), and handheld PCs. In at least one embodiment, embedded applications may include a microcontroller, a digital signal processor ("DSP"), a system-on-a-chip, network computers ("NetPCs"), set-top boxes, network hubs, wide area network ("WAN") switches, or any other system capable of performing one or more instructions according to at least one embodiment.

[0076] In at least one embodiment, computing system 900 may include, among other things, processor 902, which may include, among other things, one or more execution units 908 for performing machine learning model training and / or inference according to techniques described herein. In at least one embodiment, computing system 900 is a single-processor desktop or server system, but in another embodiment, computing system 900 may be a multiprocessor system. In at least one embodiment, processor 902 may include, among other things, a complex instruction set computing ("CISC") microprocessor, a reduced instruction set computing ("RISC*") microprocessor, a very long instruction word computing ("VLIW") microprocessor, a processor implementing a combination of instruction sets, or another processor device, such as a digital signal processor.In at least one embodiment, the processor 902 may be coupled to a processor bus 910 that transmits data signals between the processor 902 and other components in the computer system 900.

[0077] In at least one embodiment, processor 902 may include, among other things, an internal Level 1 ("L1") cache ("Cache") 904. In at least one embodiment, processor 902 may have a single internal cache or multiple levels of internal cache. In at least one embodiment, cache 904 may be external to processor 902. Other embodiments may also include a combination of both internal and external caches, depending on the particular implementation and needs. In at least one embodiment, a register file 906 may store different types of data in various registers, including, but not limited to, integer registers, floating-point registers, status registers, and instruction pointer registers.

[0078] In at least one embodiment, execution unit(s) 908, including, among other things, logic for performing integer and floating-point operations, is / are also located in processor 902. In at least one embodiment, processor 902 may also include microcode ("ucode") read-only memory ("ROM") that stores microcode for certain macroinstructions. In at least one embodiment, execution unit(s) 908 may include logic for handling a packaged instruction set 909. In one embodiment, by including a packaged instruction set 909 in an instruction set of a general-purpose processor 902, along with associated circuitry for executing instructions, operations used by many multimedia applications may be performed using packaged data in a general-purpose processor 902.In one or more embodiments, many multimedia applications may be accelerated and executed more efficiently by using the full width of a processor data bus to perform operations on packed data, which may eliminate the need to transfer smaller units of data across the processor data bus to perform one or more operations on one data item at a time.

[0079] In at least one embodiment, execution unit(s) 908 may also be used in microcontrollers, embedded processors, graphics devices, DSPs, and other types of logic circuits. In at least one embodiment, computing system 900 may include, among other things, a memory 920. In at least one embodiment, memory 920 may be implemented as a dynamic random access memory ("DRAM") device, a static random access memory ("SRAM") device, a flash memory device, or another storage device. In at least one embodiment, memory 920 may store instruction(s) 919 and / or data 921, represented by data signals, that may be executed by processor 902.

[0080] In at least one embodiment, the system logic chip may be coupled to the processor bus 910 and the memory 920. In at least one embodiment, the system logic chip may include, among other things, a memory controller hub (“MCH”) 916, and the processor 902 may communicate with the MCH 916 via the processor bus 910. In at least one embodiment, the MCH 916 may provide a high-bandwidth memory path 918 to the memory 920 for instruction and data storage and for storage of graphics commands, data, and textures. In at least one embodiment, the MCH 916 may route data signals between the processor 902, memory 920, and other components in the computing system 900, and for bridging data signals between the processor bus 910, memory 920, and a system I / O 922. In at least one embodiment, the system logic chip may provide a graphics port for coupling to a graphics controller.In at least one embodiment, the MCH 916 may be coupled to the memory 920 via a high-bandwidth memory path 918, and the graphics / video card 912 may be coupled to the MCH 916 via an Accelerated Graphics Port ("AGP") interconnect 914.

[0081] In at least one embodiment, computing system 900 may use system I / O 922, a proprietary hub interface bus, to couple MCH 916 to I / O controller hub ("ICH") 930. In at least one embodiment, ICH 930 may provide direct connections to some I / O devices via a local I / O bus. In at least one embodiment, the local I / O bus may include, among other things, a high-speed I / O bus for connecting peripherals to memory 920, chipset, and processor 902. Examples may include, but are not limited to, an audio controller 929, a firmware hub (“Flash BIOS”) 928, a wireless transceiver 926, data storage 924, a legacy I / O controller 923 containing user input and keyboard interface(s) 925, a serial expansion port 927, such as Universal Serial Bus (“USB”), and a network controller 934.Data storage 924 may include a hard disk drive, a floppy disk drive, a CD-ROM device, a flash memory device, or other mass storage device.

[0082] In at least one embodiment, Fig. 9 a system including interconnected hardware devices or “chips”, while in other embodiments Fig. 9 may illustrate an exemplary system-on-a-chip ("SoC"). In at least one embodiment, devices may be interconnected using proprietary interconnects, standardized interconnects (e.g., PCIe), or a combination thereof. In at least one embodiment, one or more components of computing system 900 are interconnected using Compute Express Link (CXL) interconnects.

[0083] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. In at least one embodiment, the inference and / or training logic 715 may be implemented in the system of Fig. 9 be used to infer or predict operations based at least in part on weight parameters computed using neural network training operations, neural network functions and / or architectures, or neural network use cases as described herein.

[0084] Such components can be used to perform augmentation of an image using a generative diffusion model while retaining important contextual or semantic content.

[0085] Fig. 10 is a block diagram illustrating an electronic device 1000 for using a processor 1010, according to at least one embodiment. In at least one embodiment, the electronic device 1000 may be, for example, among others, a notebook, a tower server, a rack server, a blade server, a laptop, a desktop, a tablet, a mobile device, a phone, an embedded computer, or any other suitable electronic device.

[0086] In at least one embodiment, system 1000 may include, among other things, processor 1010 communicatively coupled to any suitable number or type of components, peripherals, modules, or devices. In at least one embodiment, processor 1010 is coupled using a bus or interface such as a 1°C bus, a System Management Bus (“SMBus”), a Low Pin Count (LPC) bus, a Serial Peripheral Interface (“SPI”), a High Definition Audio (“HDA”) bus, a Serial Advance Technology Attachment (“SATA”) bus, a Universal Serial Bus (“USB”) (versions 1, 2, 3), or a Universal Asynchronous Receiver / Transmitter (“UART”) bus. In at least one embodiment, Fig. 10 a system including interconnected hardware devices or “chips”, while in other embodiments Fig. 10 may illustrate an exemplary system-on-a-chip ("SoC"). In at least one embodiment, Fig. 10 illustrated devices may be interconnected with proprietary interconnects, standardized interconnects (e.g., PCIe), or a combination thereof. In at least one embodiment, one or more components of Fig. 10 interconnected using Compute Express Link (CXL) interconnects.

[0087] In at least one embodiment, Fig. 10 a display 1024, a touchscreen 1025, a touchpad 1030, a near field communication unit (“NFC”) 1045, a sensor hub 1040, a thermal sensor 1046, an express chipset (“EC”) 1035, a trusted platform module (“TPM”) 1038, a BIOS / firmware / flash memory (“BIOS, FW Flash”) 1022, a DSP 1060, a drive 1020 such as a solid state drive (“SSD”) or a hard disk drive (“HDD”), a wireless local area network unit (“WLAN”) 1050, a Bluetooth unit 1052, a wireless wide area network unit (“WWAN”) 1056, a global positioning system (GPS) 1055, a camera (“USB 3.0 camera”) 1054 such as a A USB 3.0 camera and / or a low-power double data rate ("LPDDR") memory unit ("LPDDR3") 1015, for example, implemented in the LPDDR3 standard. These components may each be implemented in any suitable manner.

[0088] In at least one embodiment, other components may be communicatively coupled to processor 1010 via the components discussed above. In at least one embodiment, an accelerometer 1041, an ambient light sensor (ALS) 1042, a compass 1043, and a gyroscope 1044 may be communicatively coupled to sensor hub 1040. In at least one embodiment, a thermal sensor 1039, a fan 1037, a keyboard 1036, and a touchpad 1030 may be communicatively coupled to EC 1035. In at least one embodiment, a speaker 1063, headphones 1064, and microphone (“Mic”) 1065 may be communicatively coupled to an audio unit (“Audio Codec and Class-D Amplifier”) 1062, which in turn may be communicatively coupled to DSP 1060. For example, in at least one embodiment, the audio unit 1062 may include, among other things, an audio encoder / decoder (“codec”) and a Class-D amplifier.In at least one embodiment, the SIM card ("SIM") 1057 may be communicatively coupled to the WWAN unit 1056. In at least one embodiment, components such as the WLAN unit 1050 and Bluetooth unit 1052, as well as the WWAN unit 1056, may be implemented in a next-generation form factor ("NGFF").

[0089] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. In at least one embodiment, the inference and / or training logic 715 may be implemented in the system of Fig. 10 be used to infer or predict operations based at least in part on weight parameters computed using neural network training operations, neural network functions and / or architectures, or neural network use cases as described herein.

[0090] Such components can be used to perform augmentation of an image using a generative diffusion model while retaining important contextual or semantic content.

[0091] Fig. 11 is a block diagram of a processing system, according to at least one embodiment. In at least one embodiment, processing system 1100 includes one or more processors 1102 and one or more graphics processors 1108, and may be a single-processor desktop system, a multiprocessor workstation system, or a server system with a large number of processors 1102 or processor cores 1107. In at least one embodiment, processing system 1100 is a processing platform embodied in a system-on-a-chip (SoC) integrated circuit for use in mobile, handheld, or embedded devices.

[0092] In at least one embodiment, processing system 1100 may include or be incorporated into a server-based gaming platform, a gaming console, including a game and media console, a mobile gaming console, a handheld gaming console, or an online gaming console. In at least one embodiment, processing system 1100 is a mobile phone, a smartphone, a tablet computing device, or a mobile internet device. In at least one embodiment, processing system 1100 may also include, be coupled to, or integrated with a wearable device, such as a wearable smartwatch device, a smartglass device, an augmented reality device, or a virtual reality device.In at least one embodiment, the processing system 1100 is a television or set-top box device having one or more processors 1102 and a graphical interface generated by one or more graphics processors 1108.

[0093] In at least one embodiment, the one or more processors 1102 each include one or more processor cores 1107 to process instructions that, when executed, perform operations for system and user software. In at least one embodiment, the one and more processor cores 1107 are each configured to process a specific instruction set 1109. In at least one embodiment, the instruction set 1109 may facilitate complex instruction set computing (CISC), reduced instruction set computing (RISC), or via very long instruction word (VLIW) computing. In at least one embodiment, the processor core(s) 1107 may each process a different instruction set 1109, which may include instructions to facilitate emulation of other instruction sets.In at least one embodiment, the processor core(s) 1107 may also include other processing devices, such as a digital signal processor (DSP).

[0094] In at least one embodiment, the processor(s) 1102 may include a cache memory 1104. In at least one embodiment, the processor(s) 1102 may have a single internal cache or multiple levels of internal cache. In at least one embodiment, the cache memory is shared by various components of the processor(s) 1102. In at least one embodiment, the processor(s) 1102 also uses an external cache (e.g., a Level 3 (L3) cache or Last Level Cache (LLC)) (not shown), which may be shared by processor cores 1107 using known cache coherence techniques. In at least one embodiment, the register file 1106 is additionally included in the processor(s) 1102, which may include different types of registers for storing different types of data (e.g.,Integer registers, floating-point registers, status registers, and an instruction pointer register. In at least one embodiment, register file 1106 may include general-purpose registers or other registers.

[0095] In at least one embodiment, one or more processors 1102 are coupled to one or more interface buses 1110 for transmitting communication signals, such as address, data, or control signals, between processors 1102 and other components in processing system 1100. In at least one embodiment, the interface bus(es) 1110 may, in one embodiment, be a processor bus, such as a version of a Direct Media Interface (DMI) bus. In at least one embodiment, the interface bus(es) 1110 are not limited to a DMI bus and may include one or more Peripheral Component Interconnect buses (e.g., PCI, PCI Express), memory buses, or other types of interface buses. In at least one embodiment, the processor(s) 1102 may include an integrated memory controller 1116 and a platform controller hub 1130.In at least one embodiment, the memory controller 1116 facilitates communication between a memory device and other components of the processing system 1100, while the platform controller hub (PCH) 1130 provides connections to I / O devices via a local I / O bus.

[0096] In at least one embodiment, memory device 1120 may be a dynamic random access memory (DRAM) device, a static random access memory (SRAM) device, a flash memory device, a phase-change memory device, or other memory device having suitable performance to serve as process memory. In at least one embodiment, memory device 1120 may operate as system memory for processing system 1100 to store data 1122 and instructions 1121 for use when one or more processors 1102 are executing an application or process. In at least one embodiment, memory controller 1116 is also coupled to an optional external graphics processor 1112 that can communicate with one or more graphics processors 1108 in processor(s) 1102 to perform graphics and media operations.In at least one embodiment, a display device 1111 may be connected to the processor(s) 1102. In at least one embodiment, the display device 1111 may include one or more of an internal display device, such as in a mobile electronic device or a laptop device, or an external display device connected via a display interface (e.g., DisplayPort, etc.). In at least one embodiment, the display device 1111 may include a head-mounted display (HMD), such as a stereoscopic display device for use in virtual reality (VR) applications or augmented reality (AR) applications.

[0097] In at least one embodiment, the platform controller hub 1130 may allow peripherals to connect to the storage device 1120 and the processor(s) 1102 via a high-speed I / O bus. In at least one embodiment, I / O peripherals include, among others, an audio controller 1146, a network controller 1134, a firmware interface 1128, a wireless transceiver 1126, touch sensors 1125, and a data storage device 1124 (e.g., hard disk drive, flash memory, etc.). In at least one embodiment, the data storage device 1124 may be connected via a storage interface (e.g., SATA) or via a peripheral bus, such as a Peripheral Component Interconnect bus (e.g., PCI, PCI Express). In at least one embodiment, the touch sensors 1125 may include touchscreen sensors, pressure sensors, or fingerprint sensors.In at least one embodiment, the wireless transceiver 1126 may be a WiFi transceiver, a Bluetooth transceiver, or a mobile network transceiver such as a 3G, 4G, or Long Term Evolution (LTE) transceiver. In at least one embodiment, the firmware interface 1128 allows communication with the system firmware and may be, for example, a Unified Extensible Firmware Interface (UEFI). In at least one embodiment, the network controller 1134 may allow network connection to a wired network. In at least one embodiment, a high-performance network controller (not shown) is coupled to an interface bus(es) 1110. In at least one embodiment, the audio controller 1146 is a multi-channel high-definition audio controller. In at least one embodiment, the processing system 1100 includes an optional legacy I / O controller 1140 for coupling legacy devices (e.g.,Personal System 2 (PS / 2) devices) to the system. In at least one embodiment, the platform controller hub 1130 may also be connected to one or more Universal Serial Bus (USB) controller 1142 interface input devices, such as keyboard and mouse combinations 1143, a camera 1144, or other USB input devices.

[0098] In at least one embodiment, an instance of the memory controller 1116 and platform controller hub 1130 may be integrated into a discrete external graphics processor, such as the external graphics processor 1112. In at least one embodiment, the platform controller hub 1130 and / or the memory controller 1116 may be external to one or more processors 1102. For example, in at least one embodiment, the processing system 1100 may include an external memory controller 1116 and platform controller hub 1130, which may be configured as a memory controller hub and a peripheral controller hub within a system chipset in communication with the processor(s) 1102.

[0099] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. In at least one embodiment, portions or all of the inference and / or training logic 715 may be incorporated into the processing system 1100. For example, in at least one embodiment, training and / or inference techniques described herein may utilize one or more ALUs embodied in a graphics processor. Furthermore, in at least one embodiment, inference and / or training operations described herein may be performed using logic different from that described in Fig. 7A and / or 7B. In at least one embodiment, weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown), thereby configuring ALUs of a graphics processor to perform one or more machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0100] Such components can be used to perform augmentation of an image using a generative diffusion model while retaining important contextual or semantic content.

[0101] Fig. 12 is a block diagram of a processor 1200 having one or more processor cores 1202A-1202N, an integrated memory controller 1214, and an integrated graphics processor 1208, according to at least one embodiment. In at least one embodiment, the processor 1200 may include additional cores up to and including additional core 1202N, represented by dashed boxes. In at least one embodiment, the processor core(s) 1202A-1202N each include one or more internal cache units 1204A-1204N. In at least one embodiment, each processor core also has access to one or more shared cache units 1206.

[0102] In at least one embodiment, the internal cache unit(s) 1204A-1204N and shared cache unit(s) 1206 represent a cache hierarchy within the processor 1200. In at least one embodiment, the cache unit(s) 1204A-1204N may include at least one level of instruction and data cache within each processor core and one or more levels of shared mid-level cache, such as Level 2 (L2), Level 3 (L3), Level 4 (L4), or other levels of cache, with a highest level of cache prior to external memory classified as LLC. In at least one embodiment, cache coherence logic maintains coherence between different cache units 1206 and 1204A-1204N.

[0103] In at least one embodiment, the processor 1200 may also include a set of one or more bus controller units 1216 and a system agent core 1210. In at least one embodiment, one or more bus controller units 1216 manage a set of peripheral buses, such as one or more PCI or PCI Express buses. In at least one embodiment, the system agent core 1210 provides management functionality for various processor components. In at least one embodiment, the system agent core 1210 includes one or more integrated memory controllers 1214 for managing access to various external memory devices (not shown).

[0104] In at least one embodiment, one or more processor cores 1202A-1202N include support for simultaneous multithreading. In at least one embodiment, system agent core 1210 includes components for coordinating and operating processor cores 1202A-1202N during multithreaded processing. In at least one embodiment, system agent core 1210 may additionally include a power control unit (PCU) that includes logic and components to regulate one or more power states of processor cores 1202A-1202N and graphics processor 1208.

[0105] In at least one embodiment, processor 1200 additionally includes graphics processor 1208 to perform graphics processing operations. In at least one embodiment, graphics processor 1208 is coupled to shared cache units 1206 and system agent core 1210, including one or more integrated memory controllers 1214. In at least one embodiment, system agent core 1210 also includes a display controller 1211 to drive the graphics processor output to one or more coupled displays. In at least one embodiment, display controller 1211 may also be a separate module coupled to graphics processor 1208 via at least one interconnect or may be integrated with graphics processor 1208.

[0106] In at least one embodiment, a ring-based interconnect 1212 is used to couple internal components of processor 1200. In at least one embodiment, an alternative interconnect may be used, such as a point-to-point interconnect, a switched interconnect, or other techniques. In at least one embodiment, graphics processor 1208 is coupled to ring-based interconnect 1212 via an I / O link 1213.

[0107] In at least one embodiment, the I / O link 1213 represents at least one of several types of I / O interconnects, including an on-packet I / O interconnect that facilitates communication between various processor components and an embedded high-performance memory module 1218, such as an eDRAM module. In at least one embodiment, the processor core(s) 1202A-1202N and the graphics processor 1208 each utilize embedded memory modules 1218 as a shared last-level cache.

[0108] In at least one embodiment, the processor core(s) 1202A-1202N are homogeneous cores executing a common instruction set architecture. In at least one embodiment, the processor core(s) 1202A-1202N are heterogeneous with respect to instruction set architecture (ISA), where one or more of the processor core(s) 1202A-1202N execute a common instruction set, while one or more of the other cores of the processor core(s) 1202A-1202N execute a subset of a common instruction set or a different instruction set. In at least one embodiment, the processor core(s) 1202A-1202N are heterogeneous with respect to microarchitecture, where one or more cores having relatively higher power consumption are coupled with one or more performance cores having lower power consumption.In at least one embodiment, the processor 1200 may be implemented on one or more chips or as an SoC integrated circuit.

[0109] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. In at least one embodiment, portions or all of the inference and / or training logic 715 may be incorporated in the processor 1200. For example, in at least one embodiment, training and / or inference techniques described herein may utilize one or more ALUs incorporated in a graphics processor 1208, processor core(s) 1202A-1202N, or other components in Fig. 12. Furthermore, in at least one embodiment, inference and / or training operations described herein may be performed using logic different from that described in Fig. 7A and / or 7B. In at least one embodiment, weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown), thereby configuring ALUs of a graphics processor 1200 to perform one or more machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0110] Such components can be used to perform augmentation of an image using a generative diffusion model while retaining important contextual or semantic content. VIRTUALIZED COMPUTING PLATFORM

[0111] Fig. 13 is an example dataflow diagram for a process 1300 of generating and deploying an image processing and inferencing pipeline, according to at least one embodiment. In at least one embodiment, the process 1300 may be deployed for use with imaging devices, processing devices, and / or other device types at one or more devices 1302. The process 1300 may be executed in a training system 1304 and / or a deployment system 1306. In at least one embodiment, the training system 1304 may be used to perform training, deployment, and implementation of machine learning models (e.g., neural networks, object detection algorithms, computer vision algorithms, etc.) for use in the deployment system 1306.In at least one embodiment, deployment system 1306 may be configured to offload processing and compute resources in a distributed computing environment to reduce infrastructure requirements at device(s) 1302. In at least one embodiment, one or more applications in a pipeline may use or invoke services (e.g., inference, visualization, compute, AI, etc.) of deployment system 1306 during application execution.

[0112] In at least one embodiment, some applications used in advanced processing and inferencing pipelines may use machine learning models or other AI to perform one or more processing steps. In at least one embodiment, machine learning models may be trained at facility(ies) 1302 using data 1308 (such as imaging data) generated at facility(ies) 1302 (and stored at one or more Picture Archiving and Communication System (PACS) servers at facility(ies) 1302), may be trained using imaging or sequencing data 1308 from another facility(ies), or a combination thereof.In at least one embodiment, the training system 1304 may be used to provide applications, services, and / or other resources for generating working, deployable machine learning models for the deployment system 1306.

[0113] In at least one embodiment, the model registry 1324 may be secured by object storage, which may support version and object metadata. In at least one embodiment, the object storage may be accessible, for example, via cloud storage in a cloud platform compatible with an application programming interface (API). In at least one embodiment, machine learning models within the model registry 1324 may be uploaded, listed, modified, or deleted by developers or partners of a system interacting with an API. In at least one embodiment, an API may provide access to methods that allow users with appropriate permissions to associate models with applications so that models may be executed as part of an execution of containerized instantiations of applications.

[0114] In at least one embodiment, the training pipeline 1304 ( Fig. 13) include a scenario where a device(s) 1302 is / are training its own machine learning model, or has an existing machine learning model that needs to be optimized or updated. In at least one embodiment, imaging data 1308 generated by an imaging device(s), sequencing device(s), and / or other device types may be received. In at least one embodiment, after imaging data 1308 is received, AI-assisted annotation 1310 may be used to assist in generating annotations corresponding to the imaging data 1308 to be used as ground truth data for a machine learning model. In at least one embodiment, AI-assisted annotation 1310 may include one or more machine learning models (e.g.,convolutional neural networks (CNNs)) that can be trained to generate annotations corresponding to certain types of imaging data 1308 (e.g., from certain devices). In at least one embodiment, AI-assisted annotation 1310 can then be used directly or adapted or fine-tuned using an annotation tool to generate ground truth data. In at least one embodiment, AI-assisted annotation 1310, labeled data 1312, or a combination thereof can be used as ground truth data to train a machine learning model. In at least one embodiment, a trained machine learning model can be referred to as output model(s) 1316 and used by the deployment system 1306 as described herein.

[0115] In at least one embodiment, a training pipeline may include a scenario where a device(s) 1302 requires a machine learning model for use in performing one or more processing tasks for one or more applications in the deployment system 1306, but the device(s) 1302 may not currently have such a machine learning model (or may not have a model that is optimized, efficient, or effective for such purposes). In at least one embodiment, an existing machine learning model may be selected from a model registry 1324. In at least one embodiment, the model registry 1324 may include machine learning models trained to perform a variety of different inference tasks on imaging data.In at least one embodiment, machine learning models in model registry 1324 may have been trained on imaging data from facilities different from facility(s) 1302 (e.g., remote facilities). In at least one embodiment, machine learning models may have been trained on imaging data from one location, two locations, or any number of locations. In at least one embodiment, when trained on imaging data from a specific location, the training may take place at that location, or at least in a manner that protects the confidentiality of imaging data or restricts the transfer of imaging data off-premises. In at least one embodiment, after a model has been trained—or partially trained—at one location, a machine learning model may be added to model registry 1324.In at least one embodiment, a machine learning model may then be retrained or updated at any number of other facilities, and a retrained or updated model may be made available in model registry 1324. In at least one embodiment, a machine learning model may then be selected from model registry 1324—referred to as output model(s) 1316—and may then be used in deployment system 1306 to perform one or more processing tasks for one or more deployment system applications.

[0116] In at least one embodiment, a scenario may include device(s) 1302 that require a machine learning model for use in performing one or more processing tasks for one or more applications in deployment system 1306, but device(s) 1302 may not currently have such a machine learning model (or may not have a model that is optimized, efficient, or effective for such purposes). In at least one embodiment, a machine learning model selected from model registry 1324 may not be fine-tuned or optimized for imaging data 1308 generated at device(s) 1302 due to differences in populations, robustness of training data used to train a machine learning model, diversity of training data irregularities, and / or other issues with training data.In at least one embodiment, AI-assisted annotation 1310 may be used to assist in generating annotations corresponding to the imaging data 1308 to be used as ground truth data for retraining or updating a machine learning model. In at least one embodiment, labeled data 1312 may be used as ground truth data for training a machine learning model. In at least one embodiment, retraining or updating a machine learning model may be referred to as model training 1314. In at least one embodiment, the model training 1314—e.g., AI-assisted annotations 1310, labeled data 1312, or a combination thereof—may be used as ground truth data for retraining or updating a machine learning model.In at least one embodiment, a trained machine learning model may be referred to as output model(s) 1316 and used by the deployment system 1306 as described herein.

[0117] In at least one embodiment, deployment system 1306 may include software 1318, services 1320, hardware 1322, and / or other components, features, and functionality. In at least one embodiment, deployment system 1306 may include a software "stack" such that software 1318 may be built on top of services 1320 and may use services 1320 to perform some or all of the processing tasks, and services 1320 and software 1318 may be built on top of hardware 1322 and may use hardware 1322 to perform processing, storage, and / or other computational tasks of deployment system 1306. In at least one embodiment, software 1318 may include any number of different containers, where each container may execute an instantiation of an application.In at least one embodiment, each application may perform one or more processing tasks in an advanced processing and inference pipeline (e.g., inferencing, object detection, feature detection, segmentation, image enhancement, calibration, etc.). In at least one embodiment, an advanced processing and inference pipeline may be defined based on selections of different containers desired or required for processing imaging data 1308, in addition to containers that receive and configure imaging data for use by each container and / or for use by device(s) 1302 after processing by a pipeline (e.g., for converting outputs back to a usable data type). In at least one embodiment, a combination of containers may be implemented within software 1318 (e.g.,that comprise a pipeline) may be referred to as a virtual instrument (as described in more detail herein), and a virtual instrument may utilize services 1320 and hardware 1322 to perform some or all of the processing tasks of applications instantiated in containers.

[0118] In at least one embodiment, a data processing pipeline may receive input data (e.g., imaging data 1308) in a specific format in response to an inference request (e.g., a request from a user of a deployment system 1306). In at least one embodiment, input data may represent one or more images, video, and / or other data representations generated by one or more imaging devices. In at least one embodiment, data may be subjected to preprocessing as part of the data processing pipeline to prepare the data for processing by one or more applications.In at least one embodiment, post-processing may be performed on an output from one or more inference tasks or other processing tasks of a pipeline to prepare output data for a subsequent application and / or to prepare output data for transmission and / or use by a user (e.g., in response to an inference request). In at least one embodiment, inference tasks may be performed by one or more machine learning models, such as trained or deployed neural networks, which may include output model(s) 1316 of the training system 1304.

[0119] In at least one embodiment, data processing pipeline tasks may be encapsulated in a container(s), each representing a discrete, fully functional instantiation of an application and virtualized computing environment capable of referencing machine learning models. In at least one embodiment, containers or applications may be published in a private space (e.g., limited access space) by a container registry (described in more detail herein), and trained or deployed models may be stored in the model registry 1324 and associated with one or more applications. In at least one embodiment, images of applications (e.g.,Container images) must be available in a container registry, and after being selected by a user from a container registry for use in a pipeline, an image can be used to generate a container for an instantiation of an application for use by a user system.

[0120] In at least one embodiment, developers (e.g., software developers, clinicians, physicians, etc.) may develop, publish, and store applications (e.g., as containers) for performing image processing and / or inferencing on supplied data. In at least one embodiment, the development, publishing, and / or storage may be performed using a software development kit (SDK) associated with a system (e.g., to ensure that a developed application and / or container is consistent or compatible with a system). In at least one embodiment, an application being developed may be deployed locally (e.g., at a first device, to data from a first device) as a system (e.g., processor 1200 of Fig. 12). In at least one embodiment, because DICOM objects can contain between one and hundreds of images or other data types, and due to data variation, a developer may be responsible for managing (e.g., defining constructs for, incorporating preprocessing into an application, etc.) the extraction and preparation of incoming data. In at least one embodiment, after being validated by process 1300 (e.g., for accuracy), an application may be available in a container registry for selection and / or implementation by a user to perform one or more processing tasks on data at a user's device (e.g., a second device).

[0121] In at least one embodiment, developers may then deploy applications or containers over a network for access and use by users of a system (e.g., process 1300 of Fig. 13). In at least one embodiment, completed and validated applications or containers may be stored in a container registry, and associated machine learning models may be stored in the model registry 1324. In at least one embodiment, a requesting entity—providing an inference or image processing request—may search a container registry and / or model registry 1324 for an application, container, dataset, machine learning model, etc., select a desired combination of elements for inclusion in a data processing pipeline, and submit an image processing request.In at least one embodiment, a request may include input data (and in some examples, associated patient data) necessary to perform a request and / or may include a selection of applications and / or machine learning models to be executed in processing a request. In at least one embodiment, a request may be forwarded to one or more components of the deployment system 1306 (e.g., a cloud) to perform processing of the data processing pipeline. In at least one embodiment, processing by the deployment system 1306 may include referencing selected items (e.g., applications, containers, models, etc.) from a container registry and / or model registry 1324. In at least one embodiment, after results are generated by a pipeline, results may be provided to a user for reference (e.g.,for viewing in a viewing application suite running on a local on-premises workstation or endpoint).

[0122] In at least one embodiment, services 1320 may be used to support the processing or execution of applications or containers in pipelines. In at least one embodiment, services 1320 may include compute services, artificial intelligence (AI) services, visualization services, and / or other service types. In at least one embodiment, services 1320 may provide functionality common to one or more applications in software 1318, so that functionality may be abstracted to a service that may be invoked or consumed by applications. In at least one embodiment, functionality provided by services 1320 may run more dynamically and efficiently while also scaling well by allowing applications to process data in parallel, e.g., using a parallel computing platform 1230 ( Fig. 12). In at least one embodiment, services 1320 may be shared between and among different applications, rather than each application sharing the same functionality offered by services 1320 requiring a respective instance of services 1320. In at least one embodiment, services may include an inference server or an inference engine, which, as non-limiting examples, may be used to perform detection or segmentation tasks. In at least one embodiment, a model training service may be included, which may provide capabilities for machine learning model training and / or retraining. In at least one embodiment, a data augmentation service may further be included, which may provide GPU-accelerated data (e.g., DICOM, RIS, CIS, RESTful, RPC, raw, etc.) extraction, resizing, scaling, and / or other augmentation.In at least one embodiment, a visualization service may be used that can add image rendering effects—such as ray tracing, rasterization, denoising, sharpening, etc.—to add realism to two-dimensional (2D) and / or three-dimensional (3D) models. In at least one embodiment, virtual instrument services may be included that provide beamforming, segmentation, inferencing, imaging, and / or support for other applications within virtual instrument pipelines.

[0123] In at least one embodiment, where services 1320 include an AI service (e.g., an inference service), one or more machine learning models may be executed by invoking (e.g., as an API call) an inference service (e.g., an inference server) to execute machine learning model(s), or processing thereof, as part of application execution. In at least one embodiment, where another application includes one or more machine learning models for segmentation tasks, an application may invoke an inference service to execute machine learning models to perform one or more processing operations associated with segmentation tasks.In at least one embodiment, software 1318 implementing an advanced processing and inference pipeline including a segmentation application and an anomaly detection application may be simplified because each application may invoke a similar inference service to perform one or more inference tasks.

[0124] In at least one embodiment, hardware 1322 may include GPUs, CPUs, graphics cards, an AI / deep learning system (e.g., an AI supercomputer such as NVIDIA's DGX), a cloud platform, or a combination thereof. In at least one embodiment, different types of hardware 1322 may be used to provide efficient, dedicated support for software 1318 and services 1320 in the deployment system 1306. In at least one embodiment, the use of GPU processing may be implemented for local processing (e.g., at device(s) 1302), within an AI / deep learning system, in a cloud system, and / or in other processing components of the deployment system 1306 to improve the efficiency, accuracy, and effectiveness of image processing and generation.In at least one embodiment, software 1318 and / or services 1320 may be optimized for GPU processing related to deep learning, machine learning, and / or high-performance computing, as non-limiting examples. In at least one embodiment, at least a portion of the computing environment of deployment system 1306 and / or training system 1304 may be executed in a data center, on one or more supercomputers or high-performance computing systems, with GPU-optimized software (e.g., a combination of hardware and software from NVIDIA's DGX system). In at least one embodiment, hardware 1322 may include any number of GPUs that may be called upon to perform the processing of data in parallel, as described herein. In at least one embodiment, a cloud platform may further include GPU processing for GPU-optimized execution of deep learning tasks, machine learning tasks, or other computational tasks.In at least one embodiment, the cloud platform (e.g., NVIDIA's NGC) may be implemented as a hardware abstraction and scaling platform using an AI / deep learning supercomputer(s) and / or GPU-optimized software (e.g., as deployed on NVIDIA's DGX systems). In at least one embodiment, the cloud platform may integrate an application container clustering system or orchestration system (e.g., Kubernetes) across multiple GPUs to enable seamless scaling and load balancing.

[0125] Fig. 14 is a system diagram for an exemplary system 1400 for generating and deploying an imaging deployment pipeline, according to at least one embodiment. In at least one embodiment, the system 1400 may be used to implement the process 1300 of Fig. 13 and / or other processes including advanced processing and inference pipelines. In at least one embodiment, system 1400 may include a training system 1304 and a deployment system 1306. In at least one embodiment, training system 1304 and deployment system 1306 may be implemented using software 1318, services 1320, and / or hardware 1322 as described herein.

[0126] In at least one embodiment, system 1400 (e.g., training system 1304 and / or deployment system 1306) may be implemented in a cloud computing environment (e.g., using cloud 1426). In at least one embodiment, system 1400 may be implemented locally with respect to a healthcare provider or as a combination of cloud and local computing resources. In at least one embodiment, access to APIs in cloud 1426 may be restricted to authorized users through enforced security measures or protocols. In at least one embodiment, a security protocol may include web tokens that may be signed by an authentication service (e.g., AuthN, AuthZ, Gluecon, etc.) and may include appropriate authorization.In at least one embodiment, virtual instrument APIs (described herein), or other instantiations of system 1400, may be restricted to a set of public IPs that have been vetted or authorized for interaction.

[0127] In at least one embodiment, various components of system 1400 may communicate between themselves and each other using a variety of network types, including, but not limited to, local area networks (LANs) and / or wide area networks (WANs) via wired and / or wireless communication protocols. In at least one embodiment, communications between devices and components of system 1400 (e.g., for transmitting inference requests, for receiving results of inference requests, etc.) may be communicated via data bus(es), wireless data protocols (WiFi), wired data protocols (e.g., Ethernet), etc.

[0128] In at least one embodiment, the training system 1304 may include a training pipeline(s) 1404 similar to those described herein with respect to Fig. 13. In at least one embodiment, training pipeline(s) 1404 may be used when one or more machine learning models in deployment pipeline(s) 1410 are to be used by deployment system 1306 to train or retrain one or more (e.g., pre-trained) models and / or to implement one or more of the pre-trained models 1406 (e.g., without the need for retraining or updating). In at least one embodiment, output model(s) 1316 may be generated as a result of training pipeline(s) 1404. In at least one embodiment, training pipeline(s) 1404 may include any number of processing steps, such as, but not limited to, conversion or adaptation of imaging data (or other input data).In at least one embodiment, different training pipeline(s) 1404 may be used for different machine learning models used by the deployment system 1306. In at least one embodiment, the training pipeline(s) 1404 may be similar to a first embodiment described with respect to FIG. Fig. 13, for a first machine learning model, the training pipeline(s) 1404 may be similar to a second one with respect to Fig. 13, for a second machine learning model, and the training pipeline(s) 1404 may be similar to a third in terms of Fig. 13, for a third machine learning model. In at least one embodiment, any combination of tasks may be used within a training system 1304 depending on what is required for each machine learning model. In at least one embodiment, one or more machine learning models may already be trained and ready for deployment, so machine learning models may not be subjected to any processing by the training system 1304 and may be implemented by the deployment system 1306.

[0129] In at least one embodiment, the output model(s) 1316 and / or pre-trained model(s) 1406 may include any type of machine learning model depending on the implementation or embodiment. In at least one embodiment, machine learning models used by system 1400 may include, but are not limited to, machine learning model(s) using linear regression, logistic regression, decision trees, support vector machines (SVMs), Naive Bayes, k-nearest neighbors (Knn), K-means clustering, random forest, dimensionality reduction algorithms, gradient boosting algorithms, neural networks (e.g., auto-encoders, convolutional, recurrent, perceptrons, long / short-term / memory (LSTM), Hopfield, Boltzmann, deep belief, deconvolutional, generative adversarial, liquid state machine, etc.), and / or other types of machine learning models.

[0130] In at least one embodiment, the training pipeline(s) 1404 may include AI-assisted annotation as described herein at least with respect to Fig. 14. In at least one embodiment, labeled data 1312 (e.g., traditional annotation) may be generated through a variety of techniques. In at least one embodiment, labels or other annotations may be generated within a drawing program (e.g., an annotation program), a computer-aided design (CAD) program, a labeling program, another type of program suitable for generating annotations or labels for ground truth, and / or, in some examples, hand-drawn. In at least one embodiment, ground truth data may be produced synthetically (e.g., generated from computer models or renderings), real (e.g., designed and produced from real-world data), machine-automated (e.g., using feature analysis and learning to extract features from data and then generate labels), human-annotated (e.g.,Labeler, or annotation expert, defines the location of the labels), and / or a combination thereof. In at least one embodiment, for each instance of imaging data 1308 (or type of data used by machine learning models), there may be corresponding ground truth data generated by training system 1304. In at least one embodiment, AI-assisted annotation 1310 may be performed as part of deployment pipeline(s) 1410; either in addition to or instead of AI-assisted annotation 1310 included in training pipeline(s) 1404. In at least one embodiment, system 1400 may include a multi-tier platform including a software layer (e.g., software 1318) for diagnostic applications (or other application types) that can perform one or more medical imaging and diagnostic functions. In at least one embodiment, system 1400 (e.g.,The PACS server network may be communicatively coupled (via encrypted links) to PACS server networks of one or more institutions. In at least one embodiment, the system 1400 may be configured to access and reference data from PACS servers to perform operations such as training machine learning models, deploying machine learning models, image processing, inference, and / or other operations.

[0131] In at least one embodiment, a software layer may be implemented as a secure, encrypted, and / or authenticated API through which applications or containers may be invoked (e.g., invoked) from external environments (e.g., devices 1302). In at least one embodiment, applications may then invoke or execute one or more services 1320 to perform computational, AI, or visualization tasks associated with respective applications, and software 1318 and / or services 1320 may utilize hardware 1322 to perform processing tasks in an effective and efficient manner. In at least one embodiment, communications sent to or received from a training system 1304 and a deployment system 1306 may occur using a pair of DICOM adapters 1402A, 1402B.

[0132] In at least one embodiment, the deployment system 1306 may execute a deployment pipeline(s) 1410. In at least one embodiment, the deployment pipeline(s) 1410 may include any number of applications that may be applied sequentially, non-sequentially, or otherwise to imaging data (and / or other data types) generated by imaging devices, sequencing devices, genomics devices, etc., including AI-assisted annotation as described above. In at least one embodiment, the deployment pipeline(s) 1410, as described herein, may be referred to for an individual device as a virtual instrument for a device (e.g., a virtual ultrasound instrument, a virtual CT scan instrument, a virtual sequencing instrument, etc.).In at least one embodiment, there may be more than one deployment pipeline 1410 for a single device, depending on the information desired from data generated by a device. In at least one embodiment, if detection of irregularities from an MRI machine is desired, there may be a first deployment pipeline 1410, and if image enhancement for the output of an MRI machine is desired, there may be a second deployment pipeline 1410.

[0133] In at least one embodiment, an image generation application may include a processing task that includes the use of a machine learning model. In at least one embodiment, a user may wish to use their own machine learning model or select a machine learning model from a model registry 1324. In at least one embodiment, a user may implement their own machine learning model or select a machine learning model for inclusion in an application for performing a processing task. In at least one embodiment, applications may be selectable and customizable, and by defining constructs of applications, deployment and implementation of applications for a particular user are presented as a more seamless user experience.In at least one embodiment, by utilizing other features of system 1400—such as services 1320 and hardware 1322—deployment pipelines 1410 may be even more user-friendly, provide easier integration, and produce more accurate, efficient, and timely results.

[0134] In at least one embodiment, deployment system 1306 may include a user interface (UI) 1414 (e.g., a graphical user interface, a web interface, etc.) that may be used to select applications for inclusion in deployment pipelines 1410, arrange applications, modify or change applications or parameters or constructs thereof, use and interact with deployment pipelines 1410 during setup and / or deployment, and / or otherwise interact with deployment system 1306. In at least one embodiment, UI 1414 (or another user interface), although not illustrated with respect to training system 1304, may be used to select models for use in deployment system 1306, select models for training, or retraining, in training system 1304, and / or otherwise interact with training system 1304.

[0135] In at least one embodiment, a pipeline manager 1412 may be used, in addition to an application orchestration system 1428, to manage the interaction between applications or containers of deployment pipelines 1410 and services 1320 and / or hardware 1322. In at least one embodiment, the pipeline manager 1412 may be configured to facilitate application-to-application, application-to-services 1320, and / or application or service-to-hardware 1322 interactions. In at least one embodiment, although illustrated as being included in software 1318, which is not to be construed as limiting, in some examples, the pipeline manager 1412 may be included in services 1320. In at least one embodiment, the application orchestration system 1428 (e.g., Kubernetes, DOCKER, etc.)) may include a container orchestration system that can group applications into containers as logical units for coordination, management, scaling, and deployment. In at least one embodiment, by associating applications from deployment pipelines 1410 (e.g., a reconstruction application, a segmentation application, etc.) with individual containers, each application can be executed in a self-contained environment (e.g., at a kernel level) to increase speed and efficiency.

[0136] In at least one embodiment, each application and / or container (or image thereof) may be developed, modified, and deployed individually (e.g., a first user or developer may develop, modify, and deploy a first application, and a second user or developer may develop, modify, and deploy a second application separately from a first user or developer), which may allow focus and attention to be directed to a task of a single application and / or container without being hindered by tasks from other applications or containers. In at least one embodiment, communication and cooperation between different containers or applications may be supported by the pipeline manager 1412 and the application orchestration system 1428.In at least one embodiment, as long as an expected input and / or output from each container or application is known to a system (e.g., based on application or container constructs), the application orchestration system 1428 and / or the pipeline manager 1412 may facilitate communication among and between, and sharing of resources among, each of the applications or containers. In at least one embodiment, since one or more of the applications or containers in deployment pipelines 1410 may share the same services and resources, the application orchestration system 1428 may orchestrate, load balance, and determine the sharing of services or resources between and among different applications or containers.In at least one embodiment, a scheduler may be used to track resource requests from applications or containers, current or planned usage of those resources, and resource availability. Therefore, in at least one embodiment, a scheduler may allocate resources to different applications and distribute resources between and among applications with respect to the needs and availability of a system. In some examples, a scheduler (and / or another component of the application orchestration system 1428) may determine resource availability and distribution based on constraints imposed on a system (e.g., user constraints), such as quality of service (QoS), urgency of the need for data outputs (e.g., to determine whether to perform real-time or deferred processing), etc.

[0137] In at least one embodiment, services 1320 used and shared by applications or containers in deployment system 1306 may include compute services 1416, AI services 1418, visualization services 1420, and / or other service types. In at least one embodiment, applications may invoke (e.g., execute) one or more services 1320 to perform processing operations for an application. In at least one embodiment, compute services 1416 may be used by applications to perform supercomputing or other high-performance computing (HPC) tasks. In at least one embodiment, compute service(s) 1416 may be used to perform parallel processing (e.g., using a parallel computing platform 1430) to process data across one or more applications and / or one or more tasks of a single application, substantially simultaneously.In at least one embodiment, the parallel computing platform 1430 (e.g., NVIDIA's CUDA) may enable general-purpose computing on GPUs (GPGPU) (e.g., GPUs / Graphics 1422). In at least one embodiment, a software layer of the parallel computing platform 1430 may provide access to virtual instruction sets and parallel computing elements of GPUs for executing compute kernels. In at least one embodiment, the parallel computing platform 1430 may include memory, and in some embodiments, memory may be shared between and among multiple containers and / or between and among different processing tasks within a single container. In at least one embodiment, interprocess communication (IPC) calls may be generated for multiple containers and / or for multiple processes within a container to use the same data from a shared segment of the memory of the parallel computing platform 1430 (e.g.,B. When multiple different stages of an application or multiple applications process the same information. In at least one embodiment, instead of making a copy of data and moving data to different locations in memory (e.g., a read / write operation), the same data in the same memory location can be used for any number of processing tasks (e.g., at the same time, at different times, etc.). In at least one embodiment, when data is used to generate new data as a result of processing, that information can be stored about a new location and shared between different applications. In at least one embodiment, the location of data and a location of updated or modified data can be part of a definition of how a payload is understood within containers.

[0138] In at least one embodiment, AI services 1418 may be utilized to perform inference services for executing machine learning models associated with applications (e.g., tasked with performing one or more processing tasks of an application). In at least one embodiment, AI services 1418 may utilize AI system 1424 to execute machine learning models (e.g., neural networks such as CNNs) for segmentation, reconstruction, object detection, feature detection, classification, and / or other inference tasks. In at least one embodiment, applications of deployment pipelines 1410 may utilize one or more output models 1316 from training system 1304 and / or other models of applications to perform inference on imaging data. In at least one embodiment, two or more examples of inference using application orchestration system 1428 (e.g.,a scheduler). In at least one embodiment, a first category may include a high-priority / low-latency path that can achieve higher service level agreements, such as performing inference on urgent requests in emergency situations or for a radiologist during diagnosis. In at least one embodiment, a second category may include a standard priority path that can be used for requests that may not be urgent or when analysis can be performed at a later time. In at least one embodiment, the application orchestration system 1428 may distribute resources (e.g., services 1320 and / or hardware 1322) based on priority paths for different inference tasks of AI services 1418.

[0139] In at least one embodiment, shared storage may be connected to AI services 1418 within system 1400. In at least one embodiment, shared storage may operate as a cache (or other storage device type) and be used to process inference requests from applications. In at least one embodiment, when an inference request is sent, a request may be received by a set of API instances of deployment system 1306, and one or more instances may be selected (e.g., for best fit, for load balancing, etc.) to process a request.In at least one embodiment, to process a request, a request may be entered into a database, a machine learning model may be found from a model registry 1324 if not already in a cache, a validation step may ensure that the appropriate machine learning model is loaded into a cache (e.g., shared storage), and / or a copy of a model may be stored in a cache. In at least one embodiment, a scheduler (e.g., a pipeline manager 1412) may be used to launch an application referenced in a request if no application is already running or if there are not enough instances of an application. In at least one embodiment, an inference server may be launched if no inference server has already been launched to execute a model. A number of inference servers may be launched per model.In at least one embodiment, in a pull model where inference servers are clustered, models may be cached when load balancing is beneficial. In at least one embodiment, inference servers may be statically loaded in corresponding distributed servers.

[0140] In at least one embodiment, inference may be performed using an inference server running in a container. In at least one embodiment, an instance of an inference server may be associated with a model (and optionally, a plurality of versions of a model). In at least one embodiment, if an instance of an inference server does not exist when a request to perform inference on a model is received, a new instance may be loaded. In at least one embodiment, a model may be submitted to an inference server upon starting an inference server, so that a same container may be used to serve different models as long as an inference server runs as a different instance.

[0141] In at least one embodiment, during application execution, an inference request for a given application may be received, and a container (e.g., hosting an instance of an inference server) may be loaded (if not already loaded), and a startup operation may be invoked. In at least one embodiment, preprocessing logic in a container may perform loading, decoding, and / or other additional preprocessing on incoming data (e.g., using a CPU(s) and / or GPU(s)). In at least one embodiment, after data has been prepared for inference, a container may perform inference on data as needed. In at least one embodiment, this may include a single inference call on an image (e.g., a hand x-ray) or may require inference on hundreds of images (e.g., a chest CT).In at least one embodiment, an application may summarize results prior to completion, which may include, but is not limited to, a single confidence score, pixel-level segmentation, voxel-level segmentation, generating a visualization, or generating text to summarize findings. In at least one embodiment, different models or applications may be assigned different priorities. For example, some models may have a real-time (TAT < 1 min) priority, while others may have a lower priority (e.g., TAT < 10 min). In at least one embodiment, model execution times may be measured by a requesting institution or entity and may include partner network traversal time and execution to an inference service.

[0142] In at least one embodiment, the transfer of requests between services 1320 and inference applications may be hidden behind a software development kit (SDK), and robust transport may be provided by a queue. In at least one embodiment, a request is placed in a queue via an API for a single application / tenant ID combination, and an SDK will fetch a request from a queue and pass a request to an application. In at least one embodiment, a queue name may be provided in an environment from which an SDK will pick it up. In at least one embodiment, asynchronous communication through a queue may be useful because this may allow each instance of an application to pick up work as it becomes available.Results may be transferred back via a queue to ensure that no data is lost. In at least one embodiment, queues may also provide the ability to segment work, where highest priority work may go to a queue with the most instances of an application connected to it, while lowest priority work may go to a queue with a single instance connected to it, processing tasks in the order received. In at least one embodiment, an application may run on a GPU-accelerated instance generated in the cloud 1426, and an inference service may perform inference on a GPU.

[0143] In at least one embodiment, visualization services 1420 may be used to generate visualizations for viewing outputs from applications and / or deployment pipelines 1410. In at least one embodiment, GPUs / Graphics 1422 may be used by visualization services 1420 to generate visualizations. In at least one embodiment, rendering effects, such as ray tracing, may be implemented by visualization services 1420 to generate higher quality visualizations. In at least one embodiment, visualizations may include, among other things, 2D image renderings, 3D volume renderings, 3D volume reconstruction, 2D tomography slices, virtual reality displays, augmented reality displays, etc. In at least one embodiment, virtualized environments may be used to create a virtual interactive display or environment (e.g., a virtual environment) for interaction by users of a system (e.g., a mobile device).B. Doctors, nurses, radiologists, etc.). In at least one embodiment, visualization services 1420 may include an internal visualizer, cinematography, and / or other rendering or image processing capabilities or functionality (e.g., ray tracing, rasterization, internal optics, etc.).

[0144] In at least one embodiment, hardware 1322 may include GPUs / Graphics 1422, AI system 1424, cloud 1426, and / or other hardware used to run training system 1304 and / or deployment system 1306. In at least one embodiment, GPUs / Graphics 1422 (e.g., NVIDIA's TESLA and / or QUADRO GPUs) may include any number of GPUs used to perform processing tasks of compute services 1416, AI services 1418, visualization services 1420, other services, and / or any features or functionality of software 1318. For example, with respect to AI services 1418, GPUs / Graphics 1422 may be used to perform preprocessing on imaging data (or other data types used by machine learning models), postprocessing on outputs of machine learning models, and / or to perform inferencing (e.g., to run machine learning models).In at least one embodiment, cloud 1426, AI system 1424, and / or other components of system 1400 may utilize GPUs / graphics 1122. In at least one embodiment, cloud 1426 may include a GPU-optimized platform for deep learning tasks. In at least one embodiment, AI system 1424 may utilize GPUs, and cloud 1426—or at least a portion dedicated to deep learning or inference—may be executed using one or more AI systems 1424. As such, although hardware 1322 is illustrated as discrete components, this is not to be construed as limiting, and any components of hardware 1322 may be combined with or utilized by other components of hardware 1322.

[0145] In at least one embodiment, AI system 1424 may include a dedicated computing system (e.g., a supercomputer or HPC) configured for inference, deep learning, machine learning, and / or other artificial intelligence tasks. In at least one embodiment, AI system 1424 (e.g., NVIDIA's DGX) may include GPU-optimized software (e.g., a software stack) that may be executed using a plurality of GPUs / Graphics 1422, in addition to CPUs, RAM, storage, and / or other components, features, or functionality. In at least one embodiment, one or more AI systems 1424 may be implemented in cloud 1426 (e.g., in a data center) to perform some or all of the AI-based processing tasks of system 1400.

[0146] In at least one embodiment, cloud 1426 may include a GPU-accelerated infrastructure (e.g., NVIDIA's NGC), which may provide a GPU-optimized platform for executing processing tasks of system 1400. In at least one embodiment, cloud 1426 may include an AI system 1424 for performing one or more AI-based tasks of system 1400 (e.g., as a hardware abstraction and scaling platform). In at least one embodiment, cloud 1426 may be integrated into an application orchestration system 1428 utilizing multiple GPUs to allow seamless scaling and load balancing between and among applications and services 13 20. In at least one embodiment, the cloud 1426 may be provided for running at least some services 1320 of the system 1400, including compute services 1416, AI services 1418, and / or visualization services 1420, as described herein.In at least one embodiment, cloud 1426 may perform small and large batch inference (e.g., running NVIDIA's TENSOR RT), provide a parallel computing platform 1430 (e.g., NVIDIA's CUDA), run an application orchestration system 1428 (e.g., KUBERNETES), provide a graphics rendering API and platform (e.g., for ray tracing, 2D graphics, 3D graphics, and / or other rendering techniques for producing higher quality cinematography), and / or provide other functionality for system 1400.

[0147] Fig. 15A illustrates a dataflow diagram for a process 1500 for training, retraining, or updating a machine learning model according to at least one embodiment. In at least one embodiment, the process 1500 may be performed using a non-limiting example system 1400 of Fig. 14. In at least one embodiment, process 1500 may utilize services and / or hardware as described herein. In at least one embodiment, refined models 1512 generated by process 1500 may be executed by a deployment system for one or more containerized applications in deployment pipelines.

[0148] In at least one embodiment, model training 1514 may include retraining or updating an initial model 1504 (e.g., a pre-trained model) using new training data (e.g., new input data, such as a customer record 1506, and / or new ground truth data associated with the input data). In at least one embodiment, to retrain or update the initial model 1504, output or loss layer(s) of the initial model 1504 may be reset, deleted, and / or replaced with updated or new output or loss layer(s). In at least one embodiment, an initial model 1504 may have previously fine-tuned parameters (e.g., weights and / or biases) remaining from a previous training, such that training or retraining will not take as long or require as much processing as training a model from scratch.In at least one embodiment, during model training 1514, by resetting or replacing output or loss layers of the initial model 1504, parameters for a new dataset may be updated and retuned based on loss calculations associated with the accuracy of the output or loss layers in generating predictions on a new customer dataset 1506.

[0149] In at least one embodiment, pre-trained models 1506 may be stored in a data store or registry. In at least one embodiment, pre-trained models 1506 may have been trained, at least in part, at one or more facilities different from a facility executing process 1500. In at least one embodiment, to protect the privacy and rights of patients, subjects, or clients at different facilities, pre-trained models 1506 may have been trained on-premise using customer or patient data generated on-premise.In at least one embodiment, pre-trained models 1506 may be trained using a cloud and / or other hardware, however, confidential, privacy-protected patient data may not be transferred to, used by, or accessible from other components of a cloud (or other off-premises hardware). In at least one embodiment, when pre-trained models 1506 are trained using patient data from more than one institution, they may have been individually trained for each institution before being trained on patient or customer data from another institution. In at least one embodiment, for example, when customer or patient data has been exempted from privacy concerns (e.g., through a waiver, for experimental use, etc.) or if customer or patient data is included in a public dataset, customer or patient data is used by any number of entities to train pre-trained models 1506 on-premise and / or off-premise, such as in a data center or other cloud computing infrastructure.

[0150] In at least one embodiment, when selecting applications for use in deployment pipelines, a user may also select machine learning models to be used for specific applications. In at least one embodiment, a user may not have a model to use, so a user may select a pre-trained model(s) 1506 for use with an application. In at least one embodiment, pre-trained models may not be optimized for generating accurate results on a customer record 1506 of a user's facility (e.g., based on patient diversity, demographics, types of medical imaging devices used, etc.).In at least one embodiment, prior to deploying a pre-trained model into a deployment pipeline for use with an application(s), pre-trained models 1506 may be updated, retrained, and / or fine-tuned for use at a respective device.

[0151] In at least one embodiment, a user may select pre-trained models 1506 that need to be updated, retrained, and / or fine-tuned, and this pre-trained model may be referred to as an initial model 1504 for a training system within process 1500. In at least one embodiment, a customer data set 1506 (e.g., imaging data, genomics data, sequencing data, or other data types generated by devices at a facility) may be used to perform model training (which may include, but is not limited to, transfer learning) on ​​the initial model 1504 to generate the refined model 1512. In at least one embodiment, ground truth data corresponding to the customer data set 1506 may be generated by the model training system 1504.In at least one embodiment, ground truth data may be generated at least in part by clinicians, scientists, physicians, or medical professionals at an institution.

[0152] In at least one embodiment, AI-assisted annotation 1310 may be used in some examples to generate ground truth data. In at least one embodiment, AI-assisted annotation 1310 (e.g., implemented using an AI-assisted annotation SDK) may leverage machine learning models (e.g., neural networks) to generate suggested or predicted ground truth data for a customer record. In at least one embodiment, a user may use annotation tools within a user interface (a graphical user interface (GUI)) on a computing device.

[0153] In at least one embodiment, user 1510 may interact with a GUI via computing device 1508 to edit or fine-tune (auto)annotations. In at least one embodiment, a polygon editing feature may be used to move vertices of a polygon to more precise or fine-tuned locations.

[0154] In at least one embodiment, once the customer dataset 1506 has associated ground truth data, ground truth data (e.g., from AI-assisted annotation, manual labeling, etc.) may be used during model training to generate a refined model 1512. In at least one embodiment, the customer dataset 1506 may be applied to the initial model 1504 any number of times, and ground truth data may be used to update parameters of the initial model 1504 until an acceptable accuracy is achieved for the refined model 1512. In at least one embodiment, once the refined model 1512 has been generated, the refined model 1512 may be deployed within one or more deployment pipelines at a device for performing one or more processing tasks on medical imaging data.

[0155] In at least one embodiment, the refined model 1512 can be uploaded to pre-trained models 1542 in a model registry for selection by another facility. In at least one embodiment, this process can be performed at any number of facilities, allowing the refined model 1512 to be further refined on new datasets any number of times to generate a more universal model.

[0156] Fig. 15B is an exemplary illustration of a client-server architecture 1532 for enhancing annotation tools with pre-trained model(s) 1542, according to at least one embodiment. In at least one embodiment, AI-assisted annotation tools 1536 may be instantiated based on a client-server architecture 1532. In at least one embodiment, AI-assisted annotation tools 1536 in imaging applications may, for example, assist radiologists in identifying organs and irregularities. In at least one embodiment, imaging applications may include software tools that assist the user 1510, as a non-limiting example, in identifying a few extreme points on a particular organ of interest in raw images 1534 (e.g., in a 3D MRI or CT scan) and automatically receive annotated results for all 2D slices of a particular organ.In at least one embodiment, results may be stored in a data store as training data 1538 and used (for example, and without limitation) as ground truth data for training. For example, in at least one embodiment, when computing device 1508 sends extreme points for AI-assisted annotation, a deep learning model may receive this data as input and return inference results for a segmented organ or segmented irregularity. In at least one embodiment, pre-instantiated annotation tools, such as AI-assisted annotation tool 1536 in FIG. Fig.15B, by making API calls (e.g., API call 1544) to a server, such as an annotation assistant server 1540, which may include a set of pre-trained models 1542 stored, for example, in an annotation model registry. In at least one embodiment, an annotation model registry may store pre-trained model(s) 1542 (e.g., machine learning models, such as deep learning models) that are pre-trained to perform AI-assisted annotation 1310 on a particular organ or irregularity. These models may be further updated using training pipelines. In at least one embodiment, pre-installed annotation tools may be improved over time as new labeled data is added.

[0157] Different embodiments can be described by the following clauses: Clause 1: A computer-implemented method comprising: Removing text from an object represented in a first image; Providing the first image of the object, without the removed text, as input to a generative diffusion model; Receiving, as an output of the generative diffusion model, a second image of the object including one or more annotations about the object; and Overlaying the text into the second image of the object to cause the one or more annotations to be displayed as if they are applied to the object and the text in the second image. Clause 2: The computer-implemented method of Clause 1, wherein the one or more annotations include at least one type of defect to be applied to a representation of the object in the second image. Clause 3. A computer-implemented method as defined in Clause 2 or Clause 3, further comprising: Providing, as additional input to the generative diffusion model, a text prompt specifying at least one type or size of the one or more annotations to be generated for the object in the second image. Clause 4. A computer-implemented method according to any preceding clause, wherein removing comprises: Identifying at least a portion of the first image as the text using an optical character recognition (OCR) model; and Removing the text from the first image by setting pixel values ​​at one or more pixel locations corresponding to the identified text to pixel values ​​determined based in part on pixel values ​​of the object near the one or more pixel locations. Clause 5. The computer-implemented method of any preceding clause, wherein overlaying the text into the second image of the object allows the one or more annotations for the object in the second image to be generated by the generative diffusion model without modifying a semantic meaning of the text. Clause 6. The computer-implemented method of any preceding clause, wherein the fading is performed using a text fade weight and an annotation fade weight. Clause 7. The computer-implemented method of Clause 6, wherein said fading includes calculating a weighted pixel value average for one or more pixel locations corresponding to the text, performed according to at least one of the text fade weight or the annotation fade weight. Clause 8. A processor that includes: one or more circuits that serve the following purposes: Removing text from a texture represented in a first image; Providing the first image of the texture, after removing the text, as input to a generative diffusion model; Receiving, as output of the generative diffusion model, a second image including one or more annotations applied to the texture; and Re-fading the text into the texture, with one or more annotations, in the second image. Clause 9. The processor of Clause 8, wherein the one or more annotations include at least one type of defect to be applied to a representation of the object in the second image. Clause 10. A processor according to Clause 8 or Clause 9, wherein the one or more circuits are further configured to: Providing, as additional input to the generative diffusion model, a text prompt specifying at least one type or size of the one or more annotations to be generated for the object in the second image. Clause 11. A processor according to any one of clauses 8-10, wherein the one or more circuits further serve to: Identifying the text using an optical character recognition (OCR) model; and Removing the text from the first image by setting pixel values ​​at one or more pixel locations corresponding to the identified text to pixel values ​​determined based in part on pixel values ​​of the object near the one or more pixel locations. Clause 12. The processor of any of clauses 8-11, wherein overlaying the text into the second image of the object allows the one or more annotations for the object in the second image to be generated by the generative diffusion model without modifying a semantic meaning of the text. Clause 13. The processor of any of Clauses 8-12, wherein the fading is performed using a text fade weight and an annotation fade weight. Clause 14. The processor of any of clauses 8-13, wherein fading includes calculating a weighted pixel value average for one or more pixel locations corresponding to the text, performed according to at least one of the text fade weight or the annotation fade weight. Clause 15. A processor as defined in any of Clauses 8-14, wherein the processor comprises at least one of the following: a system for performing simulation operations; a system for performing simulation operations for testing or validating autonomous machine applications; a system for carrying out digital twinning operations; a system for performing a light transport simulation; a system for rendering graphical output; a system for performing deep learning operations; a system implemented using an edge device; a system for generating or presenting virtual reality (VR) content; a system for generating or presenting augmented reality (AR) content; a system for generating or presenting mixed reality (MR) content; a system that includes one or more virtual machines (VMs); a system that is implemented at least partially in a data center; a system for performing hardware tests using simulation; a system for performing generative content operations using a language model; a system for synthetic data generation; a system for performing generative AI operations using a large language model (LLM); a collaborative content creation platform for 3D assets; or a system implemented at least in part using cloud computing resources. Clause 16. A system comprising: one or more processors for adding one or more extensions to a texture, including semantic content in a synthetic input image, wherein the one or more processors use a generative diffusion model with a version of the synthetic input image from which the semantic content is removed to generate an output image representing the one or more extensions applied to the texture, wherein the one or more processors are further operable to blend the removed semantic content back into the texture in the output image. Clause 17. The system of Clause 16, wherein the one or more enhancements include at least one type of defect to be applied to a representation of the object in the output image. Clause 18. The system of Clause 16 or Clause 17, wherein the one or more processors are further operable to provide, as additional input to the generative diffusion model, a prompt indicating at least one type or strength of the one or more annotations to be generated for the object in the output image. Clause 19. The system of any of Clauses 16-18, wherein the one or more processors further serve to: Identifying the semantic content using an optical character recognition (OCR) model; and Removing the semantic content from the input image by setting pixel values ​​at one or more pixel locations corresponding to the identified semantic content to pixel values ​​determined based in part on pixel values ​​of the object near the pixel locations. Clause 20. A system as defined in any of Clauses 16-19, which system comprises at least one of the following: a system for performing simulation operations; a system for performing simulation operations to test or validate autonomous machine applications; a system for performing digital twin operations; a system for performing a light transport simulation; a system for rendering graphical output; a system for performing deep learning operations; a system for performing generative AI operations using a large language model (LLM); a system implemented using an edge device; a system for generating or presenting virtual reality (VR) content; a system for generating or presenting augmented reality (AR) content; a system for generating or presenting mixed reality (MR) content; a system that includes one or more virtual machines (VMs); a system that is implemented at least partially in a data center; a system for performing hardware tests using simulation; a system for performing generative content operations using a language model; a system for synthetic data generation; a collaborative content creation platform for 3D assets; or a system implemented at least in part using cloud computing resources.

[0158] Other variations are within the spirit of the present disclosure. While various modifications and alternative constructions of the disclosed techniques are possible, certain illustrated embodiments thereof are shown in the drawings and have been described in detail above. It is to be understood, however, that the disclosure is not intended to be limited to any particular form(s), but on the contrary, is intended to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of the disclosure as defined in the appended claims.

[0159] The use of the terms "a," "a," "a-," and "the," and similar designations in the context of describing disclosed embodiments (particularly in the context of the following claims) is to be construed to include both the singular and the plural, unless otherwise stated herein or clearly contradicted by context, and not as a definition of any term. The terms "comprising," "with," "including," and "containing" are to be construed as open-ended terms (i.e., "including, but not limited to") unless otherwise stated. The term "connected," when unaltered and referring to physical connections, is to be construed as partially or wholly contained, affixed, or joined, even if something in between.

[0160] Specifications of ranges of values ​​are intended merely as a shorthand method for individually referring to each value falling within the range, unless otherwise noted herein, and each value is included in the specification as if individually listed herein. In at least one embodiment, use of the term "set" (e.g., "a set of items") or "subset" is to be understood as a non-empty collection comprising one or more elements, unless otherwise noted or contradicted by context. Further, unless otherwise noted or contradicted by context, the term "subset" of a corresponding set does not necessarily denote a proper subset of the corresponding set; rather, the subset and the corresponding set may be the same.

[0161] Linking expressions such as phrases of the form "at least one of A, B, and C" or "at least one of A, B, and C," unless expressly stated otherwise or otherwise clearly contradicted by the context, are understood with the context as they are generally used to represent that an item, term, etc. can be either A or B or C or any non-empty subset of the set of A and B and C. For example, in an illustrative example of a three-element sentence, the linking expressions "at least one of A, B, and C" and "at least one of A, B, and C" refer to one of the following sentences: {A}, {B}, {C}, {A, B}, {A, C}, {B, C}, {A, B, C}. Thus, such linking expressions are not intended to generally imply that at least one of A, at least one of B, and at least one of C must be present in certain embodiments.Unless otherwise noted or contradicted by the context, the term "plural" indicates a state of plurality (e.g., "a plurality of items" refers to multiple items). A plurality is at least two elements, but can have more elements if indicated explicitly or by contact. Furthermore, unless otherwise noted or evident from the context, the phrase "based on" means "at least partly based on" and not "exclusively based on."

[0162] Operations of processes described herein may be performed in any suitable order unless otherwise specified herein or clearly contradicted by context. In at least one embodiment, a process such as the processes described herein (or variations and / or combinations thereof) is performed under the control of one or more computer systems configured with executable instructions and implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that are collectively executed on one or more processors, by hardware, or combinations thereof. In at least one embodiment, code is stored on a computer-readable storage medium, e.g., in the form of a computer program comprising a plurality of instructions executable by one or more processors.In at least one embodiment, a computer-readable storage medium is a non-transitory computer-readable storage medium that excludes transient signals (e.g., a propagating transient electrical or electromagnetic transmission) but includes non-transitory data storage circuits (e.g., buffers, cache, and queues) within transceivers for transient signals. In at least one embodiment, code (e.g., executable code or source code) is stored on a set of one or more non-transitory computer-readable storage media on which executable instructions (or other memory for storing executable instructions) are stored that, when executed (i.e., as a result of execution) by one or more processors of a computer system, cause a computer system to perform operations described herein.In at least one embodiment, a set of non-transitory computer-readable storage media comprises a plurality of non-transitory computer-readable storage media, and one or more individual non-transitory storage media of a plurality of non-transitory computer-readable storage media lack all code, while a plurality of non-transitory computer-readable storage media collectively store all code. In at least one embodiment, executable instructions are executed such that different instructions are executed by different processors—for example, a non-transitory computer-readable storage medium stores instructions, and a main central processing unit (CPU) executes some of the instructions, while a graphics processing unit (GPU) executes other instructions. In at least one embodiment, different components of a computer system have separate processors, and different processors execute different subsets of instructions.

[0163] Accordingly, in at least one embodiment, computing systems are configured to implement one or more services that alone or collectively perform operations of processes described herein, and such computing systems are configured with applicable hardware and / or software that permits operations to be performed. Furthermore, a computing system implementing at least one embodiment of the present disclosure is a single device, and in another embodiment, is a distributed computing system that includes multiple devices that operate differently such that distributed computing systems perform operations described herein and such that a single device does not perform all operations.

[0164] The use of any and all examples or exemplary terms (e.g., "such as") provided herein is intended only to better illustrate embodiments of the disclosure and is not intended to limit the scope of the disclosure unless otherwise claimed. No language in the specification should be construed to identify any unclaimed element as essential to the practice of the disclosure.

[0165] All references cited herein, including publications, patent applications, and patents, are hereby incorporated by reference to the same extent as if each reference were individually and expressly indicated to be incorporated by reference and set forth in its entirety herein.

[0166] The terms "coupled" and "connected," and their derivatives, may be used in the description and claims. It should be understood that these terms are not intended to be synonymous. Rather, in certain examples, "connected" or "coupled" may be used to indicate that two or more elements are in direct or indirect physical or electrical contact with each other. "Coupled" can also mean that two or more elements are not in direct contact with each other, but nevertheless cooperate or interact with each other.

[0167] It will be understood that, unless explicitly stated otherwise, terms such as "processing", "computing", "calculating", "determining" and the like throughout the specification refer to actions and / or processes of a computer or computing system or similar electronic computing device that manipulate data represented as physical, e.g. electronic, quantities in the registers and / or memories of the computing system and / or convert them into other data similarly represented as physical quantities in the memories, registers or other information storage, transmission or display devices of the computing system.

[0168] Similarly, the term "processor" can refer to any device or part of a device that processes electronic data from registers and / or memory and converts that electronic data into other electronic data that can be stored in registers and / or memory. As a non-limiting example, a "processor" can be a CPU or a GPU. A "computing platform" can include one or more processors. As used herein, the term "software" processes can include, for example, software and / or hardware entities that perform work over time, such as tasks, threads, and intelligent agents. Each process can also refer to multiple processes to execute instructions sequentially or in parallel, continuously or intermittently.The terms “system” and “method” are used interchangeably here, since the system may comprise one or more methods and the methods may be considered as a system.

[0169] This document may contain references to obtaining, acquiring, receiving, or inputting analog or digital data into a subsystem, computer system, or computer-implemented machine. Obtaining, acquiring, receiving, or inputting analog and digital data may be performed in various ways, e.g., by receiving data as a parameter of a function call or a call to an application programming interface. In some implementations, processes of obtaining, acquiring, receiving, or inputting analog or digital data may be performed by transferring data over a serial or parallel interface. In another implementation, processes of obtaining, acquiring, receiving, or inputting analog or digital data may be performed by transferring data over a computer network from the providing entity to the acquiring entity.It may also refer to providing, outputting, transmitting, sending, or presenting analog or digital data. In various examples, processes of providing, outputting, transmitting, sending, or presenting analog or digital data may be performed by passing data as an input or output parameter of a function call, a parameter of an application programming interface, or an interprocess communication mechanism.

[0170] While the above discussion presents example implementations of described techniques, other architectures may be used to implement described functionality, which are intended to be within the scope of the present disclosure. Furthermore, although specific distributions of responsibilities are defined above for discussion purposes, various functions and responsibilities may be distributed and allocated in different ways depending on the circumstances.

[0171] Furthermore, while the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter claimed in the appended claims is not necessarily limited to the specific features or acts described. Rather, the specific features and acts are disclosed as exemplary forms of implementing the claims.

[0172] It will be understood that the aspects and embodiments described above are exemplary only and that changes in detail may be made within the scope of the claims.

[0173] Each device, method, and feature disclosed in the description and (where applicable) in the claims and drawings may be provided independently or in any suitable combination.

[0174] The reference numbers contained in the claims are for illustrative purposes only and do not limit the scope of the claims.

Claims

[1] A computer-implemented method comprising: Removing text from an object represented in a first image; Providing the first image of the object, without the removed text, as input to a generative diffusion model; Receiving, as an output of the generative diffusion model, a second image of the object including one or more annotations about the object; and Overlaying the text into the second image of the object to cause the one or more annotations to be displayed as if they are applied to the object and the text in the second image. [2] The computer-implemented method of claim 1, wherein the one or more annotations include at least one type of defect to be applied to a representation of the object in the second image. [3] A computer-implemented method according to claim 1 or claim 2, further comprising: Providing, as additional input to the generative diffusion model, a text prompt specifying at least one type or size of the one or more annotations to be generated for the object in the second image. [4] A computer-implemented method according to any preceding claim, wherein removing comprises: Identifying at least a portion of the first image as the text using an optical character recognition (OCR) model; and Removing the text from the first image by setting pixel values ​​at one or more pixel locations corresponding to the identified text to pixel values ​​determined based in part on pixel values ​​of the object near the one or more pixel locations. [5] A computer-implemented method according to any preceding claim, wherein overlaying the text into the second image of the object allows the one or more annotations for the object in the second image to be generated by the generative diffusion model without modifying a semantic meaning of the text. [6] A computer-implemented method according to any preceding claim, wherein the fading is performed using a text fade weight and an annotation fade weight. [7] The computer-implemented method of claim 6, wherein said fading includes calculating a weighted pixel value average for one or more pixel locations corresponding to the text, performed according to at least one of the text fade weight or the annotation fade weight. [8] A processor comprising: one or more circuits that serve the following purposes: Removing text from a texture represented in a first image; Providing the first image of the texture, after removing the text, as input to a generative diffusion model; Receiving, as output of the generative diffusion model, a second image including one or more annotations applied to the texture; and Re-fading the text into the texture, with one or more annotations, in the second image. [9] The processor of claim 8, wherein the one or more annotations include at least one type of defect to be applied to a representation of the object in the second image. [10] The processor of claim 8 or claim 9, wherein the one or more circuits further serve to: Providing, as additional input to the generative diffusion model, a text prompt specifying at least one type or size of the one or more annotations to be generated for the object in the second image. [11] The processor of any of claims 8-10, wherein the one or more circuits further serve to: Identifying the text using an optical character recognition (OCR) model; and Removing the text from the first image by setting pixel values ​​at one or more pixel locations corresponding to the identified text to pixel values ​​determined based in part on pixel values ​​of the object near the one or more pixel locations. [12] The processor of any of claims 8-11, wherein overlaying the text into the second image of the object allows the one or more annotations for the object in the second image to be generated by the generative diffusion model without modifying a semantic meaning of the text. [13] The processor of any of claims 8-12, wherein the blending is performed using a text blend weight and an annotation blend weight. [14] The processor of any of claims 8-13, wherein said blending includes calculating a weighted pixel value average for one or more pixel locations corresponding to the text, performed according to at least one of the text blend weight or the annotation blend weight. [15] Processor according to any one of claims 8-14, wherein the processor consists of at least one of the following: a system for performing simulation operations; a system for performing simulation operations for testing or validating autonomous machine applications; a system for carrying out digital twinning operations; a system for performing a light transport simulation; a system for rendering graphical output; a system for performing deep learning operations; a system implemented using an edge device; a system for generating or presenting virtual reality (VR) content; a system for generating or presenting augmented reality (AR) content; a system for generating or presenting mixed reality (MR) content; a system that includes one or more virtual machines (VMs); a system that is implemented at least partially in a data center; a system for performing hardware tests using simulation; a system for performing generative content operations using a language model; a system for synthetic data generation; a system for performing generative AI operations using a large language model (LLM); a collaborative content creation platform for 3D assets; or a system implemented at least in part using cloud computing resources. [16] A system comprising: one or more processors for adding one or more extensions to a texture, including semantic content in a synthetic input image, wherein the one or more processors use a generative diffusion model with a version of the synthetic input image from which the semantic content is removed to generate an output image representing the one or more extensions applied to the texture, wherein the one or more processors are further operable to blend the removed semantic content back into the texture in the output image. [17] The system of claim 16, wherein the one or more extensions include at least one type of defect to be applied to a representation of the object in the output image. [18] The system of claim 16 or claim 17, wherein the one or more processors are further operable to provide, as additional input to the generative diffusion model, a prompt indicating at least one type or strength of the one or more annotations to be generated for the object in the output image. [19] The system of any of claims 16-18, wherein the one or more processors further serve to: Identifying the semantic content using an optical character recognition (OCR) model; and Removing the semantic content from the input image by setting pixel values ​​at one or more pixel locations corresponding to the identified semantic content to pixel values ​​determined based in part on pixel values ​​of the object near the pixel locations. [20] A system according to any one of claims 16-19, wherein the system comprises at least one of the following: a system for performing simulation operations; a system for performing simulation operations to test or validate autonomous machine applications; a system for performing digital twin operations; a system for performing a light transport simulation; a system for rendering graphical output; a system for performing deep learning operations; a system for performing generative AI operations using a large language model (LLM); a system implemented using an edge device; a system for generating or presenting virtual reality (VR) content; a system for generating or presenting augmented reality (AR) content; a system for generating or presenting mixed reality (MR) content; a system that includes one or more virtual machines (VMs); a system that is implemented at least partially in a data center; a system for performing hardware tests using simulation; a system for performing generative content operations using a language model; a system for synthetic data generation; a collaborative content creation platform for 3D assets; or a system implemented at least in part using cloud computing resources.

Images