Context preservation for composite image enhancement using diffusion

Abstract

The invention discloses context preservation for composite image enhancement using diffusion. The method presented herein is directed to generating a composite image in which one or more enhancements are vividly added to objects in the image while ensuring retention and integrity of semantic or contextual information within the image. A synthetic enhancement system may identify and extract foreground image data (e.g., text), and may process an image version from which the foreground image data has been removed by a generative diffusion model. One or more inputs may be provided to specify aspects such as the type or strength of the enhancement to be performed. After generating the enhanced image using the generative diffusion model, the previously removed text may be mixed back into the image. The synthesis enhancement system may use one or more mix weights on the text, such as defect mix weights and alphabet mix weights. The final result is a composite image with the added realistic enhancement, which retains semantic content.

Description

Background Art

[0001] There are various operations or tasks (such as may be related to animation or training data generation) for which realistic image augmentation is beneficial. For example, when training a machine learning model, it may be advantageous to include training data that represents a variety of different situations or conditions. Creating accurate and powerful deep learning models for tasks such as image recognition and interpretation may require training datasets that simulate the huge diversity and imperfections seen in the real world. Currently, a major challenge facing this field is the lack of sufficiently diverse and imperfect data that reflects real-world conditions. For example, a three-dimensional (3D) representation of a road sign or vehicle used for training may be perfect, but in the real world, these objects often have defects such as rust, dirt, raindrops, damage, and even graffiti. These imperfections can greatly affect the performance of models trained on data where such conditions do not manifest or rarely occur. Generative machine learning models can be used to synthesize images that represent at least some of these conditions, but models such as generative diffusion models may introduce transformations that may undesirably change the appearance or context of an object, such as by modifying text on a sign to which augmentation is being added, which can subsequently affect the realism of the object and the quality of machine learning models trained using images with that modified object. BRIEF DESCRIPTION OF THE DRAWINGS

[0002] Various embodiments according to the present disclosure will be described with reference to the accompanying drawings, in which:

[0003] Figures 1A-1C shows a composite image of a traffic sign according to various embodiments;

[0004] Figure 2 An example system environment including a composite variation generation system according to various embodiments is shown;

[0005] Figure 3 shows an example block diagram illustrating modules in a synthetic variation generation system according to various embodiments;

[0006] Figure 4 shows an example block diagram illustrating modules in a hybrid module according to various embodiments;

[0007] Figure 5 An example process for generating synthetic variations of an image is shown in accordance with various embodiments;

[0008] Figure 6 An example process for generating a composite image according to various embodiments is shown;

[0009] Fig. 7A Inference and / or training logic according to at least one embodiment is shown;

[0010] Figure 7B Inference and / or training logic according to at least one embodiment is shown;

[0011] Figure 8 An example data center system is shown in accordance with at least one embodiment;

[0012] Fig. 9 A computer system according to at least one embodiment is shown;

[0013] Fig.10 A computer system according to at least one embodiment is shown;

[0014] Fig.11 illustrates at least a portion of a graphics processor according to one or more embodiments;

[0015] Fig.12 illustrates at least a portion of a graphics processor according to one or more embodiments;

[0016] Fig.13 is an example data flow diagram of a high-level computing pipeline according to at least one embodiment;

[0017] Fig.14 is a system diagram of an example system for training, adapting, instantiating, and deploying machine learning models in an advanced computing pipeline according to at least one embodiment; and

[0018] Fig.15A and Fig. 15B A data flow diagram of a process for training a machine learning model, and a client-server architecture for augmenting an annotation tool with a pre-trained annotation model, according to at least one embodiment are shown. DETAILED DESCRIPTION

[0019] In the following description, various embodiments will be described. For the purpose of explanation, specific configurations and details are set forth in order to provide a thorough understanding of the embodiments. However, it will also be apparent to those skilled in the art that the embodiments may be practiced without the specific details. In addition, well-known features may be omitted or simplified to avoid obscuring the described embodiments.

[0020] The systems and methods described herein may be used by, but are not limited to, non-autonomous vehicles, semi-autonomous vehicles (e.g., in one or more advanced driver assistance systems (ADAS)), manned and unmanned robots or robotic platforms, warehouse vehicles, off-road vehicles, vehicles coupled to one or more trailers, spacecraft, boats, shuttles, emergency response vehicles, motorcycles, electric or motorized bicycles, airplanes, engineering vehicles, trains, underwater vehicles, remotely controlled vehicles (e.g., drones), and / or other vehicle types. In addition, the systems and methods described herein may be used for a variety of purposes, such as, but not limited to, machine control, machine motion, machine driving, synthetic data generation, model training or updating, perception, augmented reality, virtual reality, mixed reality, robotics, safety and surveillance, simulation and digital twins, autonomous or semi-autonomous machine applications, deep learning, environmental simulation, object or actor simulation and / or digital twins, data center processing, conversational AI, light transport simulation (e.g., ray tracing, path tracing, etc.), collaborative content creation of 3D assets, cloud computing, and / or any other suitable application.

[0021] The disclosed embodiments may be included in a variety of different systems, such as automotive systems (e.g., control systems for autonomous or semi-autonomous machines, perception systems for autonomous or semi-autonomous machines), systems implemented using robots, aviation systems, medical systems, boating systems, smart area monitoring systems, systems for performing deep learning operations, systems for performing simulation operations, systems for performing digital twin operations, systems implemented using edge devices, systems including one or more virtual machines (VMs), systems for performing synthetic data generation operations, systems implemented at least in part in a data center, systems for performing conversational AI operations, systems for performing light transport simulations, systems for performing collaborative content creation of 3D assets, systems implemented at least in part using cloud computing resources, and / or other types of systems.

[0022] Methods according to various illustrative embodiments provide for synthetic modification of image content, including the ability to introduce realistic (or stylized) modifications or enhancements (e.g., defects) to images, which themselves may be synthetically generated. Synthetic modification may be performed in such a way that any context or important aspects or features of any object represented in the image to which the enhancement is to be performed are maintained, thereby ensuring the preservation and integrity of important information in the image. For example, if the image is a traffic sign containing important text or content, the synthetic modification system may identify and extract the important text or content, such as by using an optical character recognition (OCR) tool to identify the text content, and remove or extract the text content from the image. Extraction or removal may produce an image of the object without the identified text content. The extraction process may fill in the pixel positions of the removed text based in part on the pixel values ​​of adjacent pixel positions to generate a version of the object that looks realistic but without the extracted text. This version of the object without the text is then provided as input to a generative diffusion model, for example, which may result in the generation or synthesis of a version of the image having one or more indicated enhancements added or applied to the object. Removing text from an image before processing it with a generative (e.g., latent) diffusion model can prevent the model from making unwanted transformations to the text, such as by changing characters in the text due to the diffusion process. In addition to this image, at least one cue can also be provided as an input to the diffusion model to inform one or more aspects of the enhancement to be performed, which may be related to the type and intensity of the enhancement. This can include the characteristics of the defect (e.g., rust) and its target severity (e.g., from slight to severe rust). After generating an enhanced sign image, adding the rust enhancement, the previously extracted text can be added or introduced back into the enhanced image. The synthetic enhancement system can use one or more weights for the integration process, such as defect blending weights and text blending weights, which can be used to determine the final pixel values ​​of pixel locations corresponding to text based in part on whether defects (or other enhancements) are present at these locations. Therefore, the final result can be a synthetic image with realistic enhancements (e.g., defects) added, which preserves contextual (or other underlying) information or content within the image.

[0023] A synthesis enhancement system according to at least one embodiment may provide several technical advantages and improvements. For example, the synthesis enhancement system may use a uniquely structured neural network pipeline that includes a context (or foreground) data removal stage, which ensures that important information within the image, such as text or other foreground elements, is preserved. Compared to the prior art in which the diffusion model may distort the basic information on the image, the synthesis enhancement system can prevent at least some unintentional distortion or erasure of these key details during the injection of synthetic defects by extracting basic information while applying the diffusion process. In addition, the synthesis enhancement system according to at least one embodiment can introduce a high degree of realism to synthetic defects (such as rust), ensuring that the synthetic defects are integrated with the text (such as foreground) and non-text (such as background) elements of the image. Traditional methods often encounter challenges in achieving a balance between realism and preservation of image integrity. For example, common problems may include improper 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 covers the rust, the resulting image may contradict the natural rust pattern that affects all exposed surfaces. In contrast, the synthetic enhancement system can ensure that synthetic defects (or other enhancements) are blended consistently throughout the image, affecting both background and foreground elements. The synthetic enhancement system can create a realistic blend of defects (e.g., rust) with all image components, including text. Thus, the synthetic enhancement system generates images in which synthetic defects appear to interact with all aspects of the image, mirroring the way these defects would occur under real-world conditions.

[0024] In addition, synthetic enhancement systems can effectively solve the problem of data scarcity in deep learning model training. Such systems can partially solve this problem by generating multiple variations of individual images, where these variations can contain different types and levels of enhancements or synthetic modifications. Therefore, synthetic enhancement systems can be used to increase the amount and variety of training data, thereby providing larger and more diverse data sets for model training. One benefit resulting from this is the development of more robust models that can effectively handle a variety of real-world imperfections. Therefore, synthetic enhancement systems provide significant improvements in creating realistic and diverse synthetic images while retaining important details, which is an improvement over previous methods.

[0025] It will be apparent to those skilled in the art from the teachings and suggestions contained herein that variations of this and other such functions may also be used within the scope of the various embodiments.

[0026] Figures 1A-1C Depicted is a set of images including variations of objects that can be generated using a synthetic image generation process. Figure 1A A first image 100 is shown, comprising a base image representation of a traffic sign including important contextual information, including important text in this example. Figure 1A The traffic sign shown in includes two portions, an upper portion having white letters set against a colored (e.g., red) background spelling "TOW-AWAY" and a lower portion having colored (e.g., red) letters on a white background spelling "SPECIAL PLACARD OR LICENSE PLATE REQUIRED." To increase the 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 possibly generating versions with different intensities of these imperfections (e.g., different amounts of rust, as may correspond to different ages or conditions of the sign).

[0027] Figure 1B An example synthetically modified image 110 that can be produced using a generative diffusion model is shown. In this example, Figure 1A The base image 100 in can be passed as input to a generative diffusion model, which can output a synthetically modified image 110, which can include the indicated enhancements, such as the introduction of rust on the sign. However, as shown, the synthetically modified image 110 also includes other changes to the sign that may not be desired. Although the goal is to introduce a realistic rust effect on the sign, the image output by the generative diffusion model also includes unwanted distortions of the text content of the sign. For example, "TOW-AWAY" is accidentally mutated to "T0W-^W^Y", while "SPECIAL" is incorrectly rendered as "5PECIAL". Figure 1B The grammatical distortions seen in the text are probably due to the naive This is introduced by the diffusion process, which may alter key information that should remain (substantially and recognizable) unchanged. Alternatively, existing methods may perform text removal and replacement to mitigate this distortion, but naively applying post-diffusion text replacement produces text elements that do not blend realistically with rust details. In the real world, rust affects all exposed surfaces, including text. However, in Figure 1B In the synthetically generated image 110 in FIG. , the rust appears as a layer beneath the text, which results in an unnatural, unrealistic appearance. Figure 1B Images like these may not be ideal for operations such as training machine learning models because they depict scenes that are unlikely to occur in the real world. And accurate real-world scenes may be under-represented in the training dataset.

[0028] Figure 1C Another example synthetically augmented image 120 that can be generated according to at least one embodiment is shown. In this example synthetically augmented image 120, realistic augmentations appear to be seamlessly blended into Figure 1A The synthetic enhancement system according to at least one embodiment can identify and extract contextual content, synthetically enhance an image without contextual content, and then realistically blend the extracted content back into the enhanced image. This approach can create a harmonious visual effect in which text is realistically affected (or otherwise modified) by synthetic rust. Therefore, Figure 1C The synthetically enhanced image 120 more closely mimics Figure 1A A natural and realistic alteration of a base image 100 in which rust or color changes caused by environmental factors such as air exposure and sunlight are added without undesired contextual modifications such as Figure 1B 1. A synthetically modified image 110 generated using a native diffusion generation process is shown in FIG. In at least one embodiment, the synthetic enhancement system may allow adjustment of the type and severity of such enhancements, which may be based on specific textual cues, style codes, or other such inputs. This may include a variety of possible effects or enhancements, such as different types and amounts of dirt or dust, which provides further flexibility in generating realistic synthetic images for different use cases.

[0029] Figure 2 An example system including a synthesis enhancement system according to at least one embodiment is shown. As an example, Figure 2 An example networked system 200 is shown that can be used to provide, generate, modify, encode, process and / or transmit image data or other such content. Example networked system 200 can include client device 202, other client devices 203, network 214, third party services 260, and provider environment 216 including synthesis enhancement system 230.

[0030] The client device 202 can generate or receive data for the session using components of the application 207 on the client device 202 and data stored locally on the client device 202. As an example, a user can generate a synthetic image using the application 207 using the client device 202. This can include the generation of synthetically enhanced images as discussed herein. Although only one client device 202 is shown in detail, the example networked system 200 can include one or more other client devices 203, which can communicate with the provider environment 216 via the network 214. The client device 202 can be any suitable computing device that enables a user to generate a synthetic image as described herein, and can include, for example, a desktop computer, a laptop computer, a computer workstation, a game console, a set-top box, a streaming device, a smartphone, a tablet computer, a VR headset, an AR goggles, a wearable computer, or a smart TV. In at least one embodiment, a user can generate synthetic changes using a user interface (UI) 206 running on the client device 202, although at least some functions can also be run on a remote device, a networked device, or through a cloud computing platform. In at least one embodiment, a user may provide input to the UI 206, such as through the touch-sensitive display 204 or by moving a mouse cursor displayed on the display screen. In one embodiment, a user may be able to provide input to the application 207, such as images and text prompts for generating composite images, labels, training data sets, supervision data sets. The application 207 may be provided by the provider environment 216 for download by the user on the client device 202. In at least one embodiment, the client device may include at least one processor 208 (e.g., a CPU or GPU) and memory 210 to execute the application 207 and / or perform tasks on behalf of the application 207. In at least one embodiment, the composite image generated by the application 207 may be stored locally to the local storage device 212.

[0031] In one embodiment, each client device 202 can submit a request via at least one wired or wireless network, such as the Internet, Ethernet, local area network (LAN), or cellular network, among other such options. In this example, the requests can be submitted to an address associated with a cloud provider, which can operate or control one or more electronic resources in a cloud provider environment, such as a data center or server farm. In at least one embodiment, the request can be received or processed by at least one edge server located at the edge of the network and outside of at least one security layer associated with the cloud provider environment. In this way, latency can be reduced by enabling client devices to interact with closer servers, while also improving the security of resources in the cloud provider environment.

[0032] The network 214 may represent a communication path between the client device 202, the provider environment 216, other client devices 203, and the third-party service 260. Through the network 214, the client device 202 may send input information related to the generation of the composite image through the network 214. The information may be received by a remote computing system, which may be part of the resource provider environment 216. In one embodiment, the network 214 is the Internet. The network 214 may include any appropriate network, including an intranet, the Internet, a cellular network, a local area network (LAN), or any other such network or combination, and communication on the network may be achieved through wired and / or wireless connections. The network 214 may also utilize dedicated or private communication links, which are not necessarily part of the Internet. In one embodiment, the network 214 uses standard communication technologies and / or protocols. Therefore, the network 214 may include links using technologies such as Ethernet, Wi-Fi, integrated services digital network (ISDN), digital subscriber line (DSL), asynchronous transfer mode (ATM), etc. Similarly, the network protocols used on the network 214 may include Multi-Protocol Label Switching (MPLS), Transmission Control Protocol / Internet Protocol (TCP / IP), Hypertext Transfer Protocol (HTTP), Simple Mail Transfer Protocol (SMTP), File Transfer Protocol (FTP), etc. In one embodiment, at least some of the links use mobile network technology, such as Long Term Evolution (LTE). Data exchanged through the network 214 may be represented using technologies or formats including Hypertext Markup Language (XML), Wireless Access Protocol (WAP), Short Message Service (SMS), etc. In addition, all or some of the links may be encrypted using conventional encryption technologies such as Secure Sockets Layer (SSL), Secure HTTP, or Virtual Private Network (VPN). In another embodiment, the client device 202 may use customized and / or dedicated data communication technologies instead of or in addition to the above technologies.

[0033] Provider environment 216 may include any suitable components for receiving requests and returning information or performing operations in response to those requests. Figure 2 In the illustrated embodiment, provider environment 216 may include interface 218 and server 220, which include various components for performing tasks associated with generating composite images. In at least one embodiment, provider environment 216 may include a Web server and / or an application server for receiving and processing requests and then returning data or other content or information in response to the requests.

[0034] The interface 218 can receive communications to the server 220. In at least one embodiment, the interface layer 218 can include an application programming interface (API) or other exposed interface that enables a user to submit 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, a routing component, or a load balancer. In at least one embodiment, the components of the interface layer 218 can determine the type of request or communication and can direct the request to an appropriate system or service, such as the synthesis enhancement system 230.

[0035] 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, the content application 224 executing on the server 220 (e.g., a cloud server or an edge server) may initiate a session associated with the client device 202 (e.g., using a session manager and user data stored in the user database 236), and may cause the content manager 226 to select content (e.g., one or more object representations (e.g., images)) from the object repository 234 for processing. At least a portion of the generated content (e.g., a composite image generated from the synthesis enhancement system 230) may be transmitted to the client device 202 using an appropriate transmission manager 222 for transmission via download, streaming, or another such transmission channel. An encoder may be used to encode and / or compress at least some of the data before transmitting it to the client device 202. In at least one embodiment, a client device 202 receiving such content may provide the content to a corresponding application 207 to select, provide, synthesize, modify, or use the content for presentation (or other purposes) on or by the client device 202. The decoder may also be used to decode data received via one or more networks 214 for presentation via the client device 202, such as presentation of image or video content via a touch-sensitive display 204. In at least one embodiment, at least some of the content may already be stored on the client device 202, rendered on the client device 202, or accessible by the client device 202, such that at least the portion of the content does not need to be transmitted over the network 214, such as the content may have been previously downloaded or stored locally on a hard disk or optical disk. In at least one embodiment, the content may be transmitted from the server 220 or the user database 236 to the client device 202 using a transmission mechanism such as data streaming. In at least one embodiment, at least a portion of the content may be obtained, enhanced, and / or streamed from another source (e.g., third-party service 260 or other client device 203), which may also include a content application 262 for generating, enhancing, or providing the content. In at least one embodiment, multiple computing devices or multiple processors within one or more computing devices (e.g., which may include a combination of CPUs and GPUs) may be used to perform portions of this functionality.

[0036] In at least one embodiment, the server 220 may include a processor such as a central processing unit (CPU). However, in at least one embodiment, resources in such an environment may utilize a GPU to process data for at least some types of requests. In at least one embodiment, GPUs (with thousands of cores) are designed to handle massively parallel workloads, and therefore have become very popular for training neural networks and generating predictions in deep learning. In at least one embodiment, while using GPUs for offline construction can train larger and more complex models faster, generating predictions offline means that input features cannot be used when requested, or predictions must be generated for all feature permutations and stored in a lookup table to serve real-time requests. In at least one embodiment, if the deep learning framework supports CPU mode and the model is small and simple enough to perform feedforward on the CPU with reasonable latency, the service on the CPU instance can host the model. In at least one embodiment, training can be performed offline on the GPU and reasoning can be performed in real time on the CPU. In at least one embodiment, if the CPU approach is not a viable option, the service can run on a GPU instance. However, in at least one embodiment, because GPUs have different performance and cost characteristics than CPUs, running a service that offloads runtime algorithms to GPUs may require designing them differently from CPU-based services.

[0037] Server 220 may include content application 224, which includes content manager 226 and synthesis enhancement system 230. As previously discussed, content manager 226 may send objects (e.g., images) from object repository 234 to synthesis enhancement system 230 along with requests and other data from client device 202 to generate a synthetic image. Synthesis enhancement system 230 may generate a synthetic image with variations such as defects and provide the results to transmission manager 222 for transmission back to client device 202. Synthesis enhancement system 230 may also use local data sets or data sets provided by third-party service 260 to train machine learning models that can generate synthetic images and store the trained models in a model repository. Figure 3 Functionality associated with synthesis enhancement system 230 is discussed in greater detail.

[0038] Figure 3Components of an example composition enhancement system 230 are shown in accordance with at least one embodiment. Composition enhancement system 230 may include a foreground identification and extraction module 302 that may identify "foreground" content of an image, such as text, characters, symbols, or other contextual elements to be preserved throughout an enhancement or modification process. Foreground identification and extraction module 302 may include an OCR component that may identify pixels corresponding to text, and an extraction component that is used to "remove" text from an image by modifying pixel values ​​at pixel locations of text based on values ​​of neighboring pixels so that the image appears as if the text is not present in the image, but the appearance of the object is preserved. The "removed" text (e.g., may include pixel values ​​corresponding to pixel locations of the identified text) may be stored to a foreground data repository, such as a cache memory or other temporary storage. Composition enhancement system 230 also includes a trained generative diffusion model 304 that may take an image (with the foreground removed) as input and generate a composite image (or image data) having one or more enhancements added to or otherwise present in the image. The synthesis enhancement system also includes a blending module 306 that can blend the removed foreground data from the temporary storage 308 back into the image including the enhancement using one or more blending weights determined by the blending module 306. If the enhancement system also performs training, the system can include a training data repository 324 and can store the enhanced image 322 as training data for training a model, which can be selected from a model repository 326 that stores untrained models and / or trained models in at least one embodiment.

[0039] The synthetic enhancement system 230 may operate by receiving a request to generate a synthetic change or enhancement of an input image 310. The input image may include a foreground portion and a background portion, the foreground portion such as (for example but not limited to): text, text information, decal-like overlays, graphic overlays, graphic symbols, symbols, characters, letters, etc. The synthetic enhancement system 230 may separate the foreground information or any details that need to be preserved from the image. The separated background image data may then be processed by a diffusion model 304, which introduces changes or enhancements (e.g., defects) into the image. The enhancement may be specified by one or more instances of enhancement input 312, which may take the form of a text prompt, voice input, style code, or other such input. The enhancement input may indicate one or more types of enhancements to be added or generated, such as rust, dust, graffiti, decay, mold, or other damage, and the amount, degree, or intensity of the enhancement, where an intensity of rust enhancement of 0 may indicate that no rust is added, and an intensity of rust enhancement of 1 may indicate that the sign appears to be completely rusted, with values ​​between 0 and 1 indicating the relative amount of rust. The image generated according to the enhancement input 312 may then be reintroduced into the foreground. As previously described, the blending module 306 can calculate letter (or other content) blending weights and defect (or other enhancement) blending weights, which can be used to determine how to blend previously removed foreground information back into the enhanced image 322. The blending module 306 can ensure that the reintroduced foreground blends harmoniously, affected by the added defects, while maintaining the original semantics. The following sections will discuss each module in the synthesis enhancement system 230 in more detail.

[0040] In at least one embodiment, the foreground identification and extraction module 302 can detect and extract pixel values ​​corresponding to foreground information from the input image. As used herein, foreground information can refer to elements in an image, where these elements carry semantic or contextual meaning, which may be expected to remain unchanged throughout the synthetic enhancement process. In other words, despite the introduction of changes or modifications, the inherent meaning, expression or value of these foreground elements remains consistent. In at least one embodiment, the foreground can range from textual information (such as letters on a sign) to visual data (such as decals) or symbols (such as wheelchair accessible symbols, arrows or crosswalk signs). In order to separate textual information, the foreground identification and extraction module 302 can apply OCR (optical character recognition) or other content recognition models, algorithms or processes, allowing the module to detect and identify any text present in the input image, or at least text that is determined to be potentially important based on factors in the image (such as size or position). For non-textual elements, such as decals or symbols, the module can use pattern recognition techniques or trained machine learning algorithms to detect specific shapes or symbols. Once the necessary foreground information is identified, the foreground identification and extraction module 302 will continue 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 of only 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 that retains only the pixels corresponding to the text information. The foreground identification and extraction module 302 may use an OCR model to identify the area containing the text, extract the foreground data of the image mask corresponding to the pixels corresponding to the identified foreground data, and save the extracted foreground data as a new image or mask with pixels corresponding to the foreground. This mask may then 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, thereby obtaining an image with only the background information for use in the diffusion process.

[0041] The generative diffusion model 304 (or other appropriate generative model, network or process) can process the image after removing the foreground and add changes or enhancements to the image, thereby focusing on the background or other parts of the image. As used herein, the background of the image can refer to the image after removing the foreground, or the pixel locations corresponding to a specific object in the image after removing the foreground. For example, if rust is to be applied to a sign in an image, the diffusion model will be fully trained to apply the rust only to the sign, and not to the background bushes, grass, sky, or other objects that may be in the "background" of the image. The diffusion model 304 introduces realistic changes or defects, such as rust or wear, to the image, simulating the effects of the natural environment on the image objects. The diffusion model 304 can be a generative model, such as an image-to-image diffusion model. The working principle of the image-to-image diffusion model is to take an input image and denoise it according to the model parameters, which produces an image containing more changes (i.e., smart noise). In one or more embodiments, the diffusion model 304 can take as input an image from which the foreground has been removed. The diffusion model 304 can obtain additional inputs, such as text prompts, which provide guidance on the nature and intensity of the defects (noise) to be introduced. For example, the hint may specify, for example but not limited to: "mild rust", "heavy rust", "five years of sun exposure", etc. The diffusion model 304 may start with an input image and gradually add (intelligent) noise to it in a series of steps. The diffusion model 304 may gradually refine these noisy data back to an image in iterative steps. Each refinement iteration aims to reduce the noise and improve the image quality to obtain a realistic image of one or more objects of the type or category for which the model was trained. Each refinement step aims to predict the noise added in 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 given the noisy data at each step. In a series of steps, the model gradually refines the noisy data back to an image, aiming to reduce the noise and restore the image before the noise addition stage.

[0042] In one embodiment, the diffusion model 304 can also adjust the extent and character of the changes introduced to the image. For example, the intensity of the change can be controlled, and the diffusion model 304 can simulate the effects of different severity, such as the subtle changes produced by five years of rust versus the effects of a hundred years of corrosion. Textual prompts can also be used to control the content of graffiti or the type of lighting conditions. In addition, the diffusion model 304 can adjust the nature of the changes in response to specified prompts. These prompts can be used to specify a wide range of potential modifications. This includes environmental effects such as dust, rust, rain, and fog, adding contextual elements such as objects that may appear on the street (such as pedestrians or crosswalks), adjusting the atmosphere of the image by modifying lighting and shadows, and generating defects such as cracks or scratches. The diffusion model 304 can also be guided to incorporate elements such as graffiti based on textual prompts. The output image from the diffusion model 304 is a modified image into which the requested changes (such as defects) have been incorporated. For convenience, in the following discussion, this modified image may also be referred to as a diffusion image. Once the diffusion image is generated, it is provided to the blending module 306 for further processing, which will be based on the text prompt. Figure 4 Provide detailed explanation.

[0043] The blending module 306 may blend the previously removed foreground information back into the enhanced image 322 . Figure 4 An example component of such a blending module 306 is shown. The blending module 306 may include a dominant color finder 404 that identifies a dominant color and a blending weight determination module 406 that determines parameters associated with the blending process. Since a stable diffusion process typically results in an array of color variations around what was originally a single color in the input image, the blending module 306 may determine one or more dominant colors in the diffuse image. After identifying the dominant color, the blending module 306 may use the dominant color to determine how to combine elements of the image, such as foreground, letters, background, and defects. In one embodiment, the blending module 306 may determine the appropriate blending of variations (e.g., defects) and foreground (e.g., text) based on the degree to which each pixel behind the foreground deviates from the dominant color. For example, consider a scene where the background of a sign is red and the letters are white. If the color of a particular pixel behind the text is closer to the dominant red, the system will blend more white letters into that pixel. If the pixel deviates significantly from the mean red (perhaps due to the presence of a rust defect), the blending module 306 will assign a greater weight to the defect. The functionality associated with each of modules 404 and 406 will be discussed in further detail below.

[0044] The dominant color finder 404 can identify the dominant colors in the image. As variations are added, the image output by the diffusion model 304 can include complex colors. For example, consider a traffic sign that initially displays only red and white. After being processed by the diffusion model 304, the sign may now display multiple shades within the red and white spectrum, perhaps including orange and brown tones to simulate a rust effect. 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.

[0045] The color analysis module 410 may perform a color spectrum analysis. The color analysis module 410 may use a hyperparameter that specifies the number of colors that occur most frequently on the original image. The color analysis module 410 may find multiple colors that occur most frequently based on the hyperparameter. For example, in the case of a stop sign (which is originally red and white), the diffusion image may display various shades of red and white after being processed by the diffusion model 304. If the hyperparameter that specifies the number of most common colors in the image is set to 30, the color analysis module 410 may classify all unique RGB colors present in the image and select the most common 30 colors. In this particular example, the color analysis module 410 may identify multiple variations of red and white because these are the dominant colors in the image. Most of the identified hues are closely related to red or white, but may show a wide range of color variations in hue. The color variations identified by the color analysis module 410 may be passed to the color clustering module 412 for further processing.

[0046] The color clustering module 412 groups the colors identified by the color analysis module 410. In one embodiment, the color clustering module 412 can group the colors identified by the color analysis module 410 into clusters using a machine learning or clustering algorithm. The color clustering module 412 can calculate a mean color based on the values ​​in the cluster, and the mean color can be considered a dominant color. In one embodiment, the mean color is calculated by averaging the individual red, green, and blue (RGB) color component values ​​of all pixels in the cluster. For each pixel in the cluster, the RGB values ​​are summed separately, and then the sum is divided by the total number of pixels in the cluster to obtain three means corresponding to each RGB component. The resulting mean color represents the "average" color of all pixels within that particular cluster.

[0047] The color clustering module 412 may also use a parameter (e.g., M) to specify the maximum number of dominant colors. The parameter M guides the process by setting a limit on the most frequently occurring colors to be considered when identifying dominant colors. For example, in the case of a stop sign with white text on a red background, the parameter M may be set to 2, indicating that two dominant colors should be considered, which may be specific shades of white and red. In one embodiment, the color clustering module 412 trains and uses a clustering model that accepts as input the number of desired clusters and aligns the number of clusters with the maximum number of most frequently occurring colors. This results in the formation of color groups that align with the primary colors present in the image. In one embodiment, the color clustering module 412 may employ a clustering model that is autonomously optimized and not limited to a pre-specified number of clusters. In this case, the color clustering module 412 will focus on the largest M clusters among the clusters formed to determine the dominant colors. Using the case of the stop sign as an illustrative example, the color clustering module 412 may be directed to set the maximum number of most frequently occurring colors to 2 (e.g., M=2). The color clustering module 412 receives the most common 30 colors in the diffusion image from the color analysis module and proceeds to classify these colors into different groups. From these groups, the color clustering module 412 can identify the two largest clusters. In the specific example of the stop sign, these two clusters may include various shades of red and white. The color clustering module 412 then determines the mean color for each of the two clusters, which is then assigned as the dominant color of the image.

[0048] The blending weight determination module 406 can determine parameters for blending the foreground and the changes back into the image (e.g., by using the blending execution module 408) to produce a final composite image with the generated changes. In one embodiment, the blending weight determination module 406 determines letter blending weights and defect blending weights for determining the degree of blending of letters and defects of the pixel. The letter blending weights can determine the degree of blending of foreground elements, which can be text information, etc. Although the term "letters" is used, the blending weights can be applied to any form of foreground details to be blended back into the image. The defect blending weight determines the blending strength of the effect (e.g., defect) caused by the change or synthesis. Although the term "defect" is used, this weight can be used to blend any change or effect that is desired to be incorporated into the image. The blending weight determination module 406 can then use the letter blending weights and defect blending weights to blend the foreground back into the image. In one embodiment, the blending process is performed on a pixel-by-pixel basis. For each individual pixel that is part of a foreground element (such as text or a symbol), the corresponding blending weight is derived from the matching pixel in the diffused or changed image. In other words, the blending weight is determined based on the characteristics of the pixel of the diffused image that the foreground pixel will cover. In the case where a pixel of the diffused image deviates significantly from the dominant color, it can be inferred that the pixel in question has been strongly affected by the defect. Therefore, the defect blending weight is assigned a higher value. Conversely, if a pixel of the diffused image is very similar to the dominant color, it indicates that the pixel has not been substantially changed, which results in the letter blending weight being assigned a higher value.

[0049] In at least one embodiment, the blending weight determination module 406 may determine the weight using a threshold. In one embodiment, the deviation is quantified using an algorithm that uses a distance measure in the color space. The distance measure may be a Euclidean distance, a Manhattan distance, or any other relevant distance measure in the color space. If the calculated deviation of a pixel exceeds a threshold, the blending weight determination module 406 may determine that the pixel is strongly affected by a defect, and therefore assign a higher defect blending weight. If the deviation is below the threshold, it indicates that the pixel is closer to the dominant color, and therefore assigns a higher letter blending weight. In another embodiment, the blending weight determination module 406 may determine the weight using a function of the deviation. For example, the defect blending weight may be an increasing function (e.g., a linear function or an exponential function) of the deviation, and the letter blending weight may be a decreasing function of the deviation. In one embodiment, a machine learning technique may be used to determine the blending weight. A model may be trained to predict weights based on the deviation, possibly taking into account other features such as the spatial location of the pixel, the color distribution in the pixel neighborhood, and the like.

[0050] Figure 5 An example process flow is depicted, including an example image illustration for creating a composite image with added variation. Figure 5, image 510 is an input image that includes a representation of a traffic sign divided into two parts. The top part has the letters "TOW-AWAY" on a red background, and the lower part has the letters "SPECIAL PLACARD ORLICENSE PLATE REQUIRED" on a white background. The goal is to incorporate a rust effect into the traffic sign shown in image 510.

[0051] Foreground identification and extraction 302 may first perform a foreground removal process 511 by extracting the foreground (e.g., text) from an image 510. Two instances of image data are generated by the foreground removal process 511, including an image 520 corresponding to background image data with text removed, and image data 530 corresponding to the "removed" pixel values ​​corresponding to the extracted text. After the foreground removal process 511, the background image 520 undergoes an enhancement process 512 by being passed as input to the diffusion model 304. For example, given a text cue and a background image 520, the diffusion model 304 may generate an enhanced image 540, wherein defects are now incorporated into the background image 520. While the original input image 510 may have only flat red and flat white, the enhanced image 540 may have various shades and hues of red and white, as well as colors associated with rust, such as brown and orange.

[0052] Then, the blending module 306 can perform a blending process 513, including the extracted foreground image data 530 and the enhanced image data 540. The dominant color finder 404 of the blending module 306 can determine the dominant colors in the enhanced image 540. Since the enhanced image 540 may have a complex color scheme due to the defect generation process, the dominant color finder 404 can first determine the number of most frequently occurring colors and cluster the colors. The dominant colors are determined by averaging the colors in each cluster. In this particular example, the number of dominant colors can be set to two, and the two dominant colors can be red and white. In order to determine how to blend each pixel in the foreground image 530 into the final image, the blending weight determination module 406 determines the alphabetical blending weight and the defect blending weight. These weights indicate how each pixel in the foreground image 530 will be blended with the enhanced image 540. If the position of a pixel in the enhanced image 540 matches that of a pixel in the foreground image 530, the blending module 306 determines the weight based on the deviation of the pixel color in the enhanced image 540 from the dominant color. The final image 550 is produced by blending the text back into the enhanced image 540 .

[0053] Figure 6An example process 600 for generating a composite image with one or more enhancements that can be performed according to at least one embodiment is shown. It should be understood that for this process and other processes herein, additional, fewer or alternative steps can be performed in a similar or alternative order or at least partially in parallel within the scope of various embodiments. In addition, although described with respect to text, it should be understood that other contextual, semantic or important elements can also be removed and also mixed back into the object or region of the enhanced image, unless otherwise explicitly stated. In this example, an image is obtained 610, which includes at least one representation of an object to which enhancement is to be performed. Text (or other semantic or contextual content or elements) can be identified 620 and removed from the image, such as by modifying pixels corresponding to these pixel positions and storing pixel values ​​of the removed content, as discussed herein. The image of the object (without the removed text or content) can be provided 630 as input to a generative diffusion model. An enhanced image of the object as an output of the generative diffusion model can be received 640, the enhanced image including one or more enhancements added to the object. The removed text may then be blended 650 back into the object in the enhanced image using one or more blending weights to allow realistic blending in areas with and without added enhancements or other image changes. An enhanced image may then be provided 660 as an output, e.g., for presentation in a game or animation, or for use as training data, among other such options, the enhanced image including a representation of the object having the text present in the input image and one or more enhancements realistically applied.

[0054] Reasoning and training logic

[0055] Fig. 7A Inference and / or training logic 715 is shown for performing reasoning and / or training operations associated with one or more embodiments. Fig. 7A and / or Figure 7B Details regarding the inference and / or training logic 715 are provided.

[0056] In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, code and / or data storage 701 for storing forward and / or output weights and / or input / output data, and / or other parameters for configuring 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 training logic 715 may include or be coupled to code and / or data storage 701 for storing graph code or other software to control timing and / or sequence, where weights and / or other parameter information is loaded to configure logic, including integer and / or floating point units (collectively referred to as arithmetic logic units (ALUs)). In at least one embodiment, the code (such as graph code) loads weights or other parameter information into a processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, the code and / or data storage 701 stores input / output data during training and / or inference using aspects of one or more embodiments and / or weight parameters during forward propagation of each layer of a neural network trained or used in conjunction with one or more embodiments. In at least one embodiment, any portion of code and / or data storage 701 may be included within other on-chip or off-chip data storage, including a processor's L1, L2, or L3 cache or system memory.

[0057] 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 random access memory ("DRAM"), static random access memory ("SRAM"), non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, the choice of whether code and / or data storage 701 is internal or external to a processor, for example, or consists of DRAM, SRAM, flash memory, or some other storage type, may depend on the available storage space on-chip or off-chip, the latency requirements of the training and / or inference functions being performed, the batch size of the data used in inference and / or training of the neural network, or some combination of these factors.

[0058] In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, code and / or data storage 705 for storing reverse 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, during training and / or inference using aspects of one or more embodiments, the code and / or data storage 705 stores weight parameters and / or input / output data for each layer of a neural network trained or used in conjunction with one or more embodiments during back propagation of input / output data and / or weight parameters. 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 to control timing and / or sequence, wherein weights and / or other parameter information is loaded to configure logic including integer and / or floating point units (collectively referred to as arithmetic logic units (ALUs)). In at least one embodiment, code (such as graph code) loads weights or other parameter information into a processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, any portion of code and / or data storage 705 may be included with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory. In at least one embodiment, any portion of 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, 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 code and / or data storage 705 is internal or external to the processor, for example, whether it is composed of DRAM, SRAM, flash memory, or some other storage type, depends on whether the available storage is on-chip or off-chip, the latency requirements of the training and / or inference functions being performed, the data batch size used in the inference and / or training of the neural network, or some combination of these factors.

[0059] 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 the processor's L1, L2, or L3 cache or system memory.

[0060] In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, one or more arithmetic logic units (“ALUs”) 710 (including integer and / or floating point units) for performing logical and / or mathematical operations based at least in part on or as directed by training and / or inference code (e.g., graph code), the results of which may produce activations (e.g., output values ​​from a layer or neuron within a neural network) stored in activation storage 720, which is a function of input / output and / or weight parameter data stored in code and / or data storage 701 and / or code and / or data storage 705. In at least one embodiment, activations are performed in response to executing instructions or other code, linear algebra and / or matrix-based mathematics performed by ALU 710 to generate activations stored in activation storage 720, where weight values ​​stored in code and / or data storage 701 and / or code and / or data storage 705 are used as operands 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-chip or off-chip storage.

[0061] In at least one embodiment, one or more ALUs 710 are included in one or more processors or other hardware logic devices or circuits, while in another embodiment, one or more ALUs 710 may be outside a processor or other hardware logic device or circuit that uses them (e.g., a coprocessor). In at least one embodiment, one or more ALUs 710 may be included within an execution unit of a processor, or otherwise included in a group of ALUs accessible by an execution unit of a processor, which may be within the same processor or distributed between different processors of different types (e.g., a central processing unit, a graphics processing unit, a fixed function unit, etc.). In at least one embodiment, code and / or data storage 701, code and / or data storage 705, and activation storage 720 may be on the same processor or other hardware logic device or circuit, while in another embodiment, they may be in different processors or other hardware logic devices or circuits or some combination of the same and different processors or other hardware logic devices or circuits. In at least one embodiment, any portion of activation storage 720 may be included with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory. Additionally, 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 the processor's fetch, decode, schedule, execute, exit, and / or other logic circuitry.

[0062] In at least one embodiment, activation storage 720 may be cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, activation storage 720 may be completely or partially internal or external to one or more processors or other logic circuits. In at least one embodiment, activation storage 720 may be selected to be internal or external to a processor, for example, or include DRAM, SRAM, flash memory, or other storage types, depending on the storage available on-chip or off-chip, the latency requirements for performing training and / or inference functions, the batch size of data used in inferencing and / or training neural networks, or some combination of these factors. In at least one embodiment, Fig. 7A The inference and / or training logic 715 shown in FIG. 7 may be used in conjunction with an application specific integrated circuit (“ASIC”), such as the ASIC from Google. Processing unit from Graphcore TM Inference Processing Unit (IPU) from Intel (e.g., "LakeCrest") processor. In at least one embodiment, Fig. 7A The illustrated inference and / or training logic 715 may be used in conjunction with central processing unit (“CPU”) hardware, graphics processing unit (“GPU”) hardware, or other hardware such as a field programmable gate array (“FPGA”).

[0063] Figure 7B Inference and / or training logic 715 is shown in accordance with at least one or more embodiments. In at least one embodiment, the reasoning and / or training logic 715 may include, but is not limited to, hardware logic in which computing resources are dedicated or otherwise uniquely used in conjunction with weight values ​​or other information corresponding to one or more layers of neurons within a neural network. In at least one embodiment, Figure 7B The inference and / or training logic 715 shown in FIG. 7 may be used in conjunction with an application specific integrated circuit (ASIC), such as the ASIC from Google. Processing unit from Graphcore TM Inference Processing Unit (IPU) from Intel (e.g., "LakeCrest") processor. In at least one embodiment, Figure 7BThe inference and / or training logic 715 shown in can be used in conjunction with central processing unit (CPU) hardware, graphics processing unit (GPU) hardware, or other hardware (e.g., field programmable gate array (FPGA)). In at least one embodiment, the inference and / or training logic 715 includes, but is not limited to, code and / or data storage 701 and code and / or data storage 705, which can 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. Figure 7B In at least one embodiment shown in , each of code and / or data storage 701 and code and / or data storage 705 is associated with a dedicated computing resource (e.g., computing hardware 702 and computing hardware 706), respectively. In at least one embodiment, each of computing hardware 702 and computing hardware 706 includes one or more ALUs that perform mathematical functions (e.g., linear algebraic functions) solely on the information stored in code and / or data storage 701 and code and / or data storage 705, respectively, and the results of performing the functions are stored in activation storage 720.

[0064] In at least one embodiment, each of the code and / or data stores 701 and 705 and the corresponding computing hardware 702 and 706 corresponds to a different layer of the neural network, such that activations from one "storage / compute pair 701 / 702" of the code and / or data store 701 and computing hardware 702 are provided as inputs to the next "storage / compute pair 705 / 706" of the code and / or data store 705 and computing hardware 706, so as to reflect the conceptual organization of the neural network. In at least one embodiment, each storage / compute pair 701 / 702 and 705 / 706 can correspond to more than one neural network layer. In at least one embodiment, additional storage / compute pairs (not shown) can be included in the inference and / or training logic 715 after or in parallel with the storage / compute pairs 701 / 702 and 705 / 706.

[0065] Data Center

[0066] Figure 8 An example data center 800 is shown 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.

[0067] In at least one embodiment, Figure 8As shown, the data center infrastructure layer 810 may include a resource coordinator 812, grouped computing resources 814, and node computing resources ("node CRs") 816(1)-816(N), where "N" represents any positive integer. In at least one embodiment, the node CRs 816(1)-816(N) may include, but are not limited to, 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 drives or disk drives), network input / output ("NWI / 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 above computing resources.

[0068] In at least one embodiment, the grouped computing resources 814 may include a separate grouping (not shown) of node CRs housed in one or more racks, or many racks (also not shown) housed in data centers at various geographic locations. The separate grouping of node CRs within the grouped computing resources 814 may include computing, networks, memory, or storage resources that can be configured or allocated to support groupings of one or more workloads. In at least one embodiment, several node CRs including a CPU or processor 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.

[0069] In at least one embodiment, resource coordinator 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 coordinator 812 may include a software design infrastructure ("SDI") management entity for data center 800. In at least one embodiment, resource coordinator 812 may include hardware, software, or some combination thereof.

[0070] In at least one embodiment, Figure 8As shown, the 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 that supports 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 the application 842 may include a web-based service software or application, such as a service or application provided by Amazon Web Services, Google Cloud, and Microsoft Azure. In at least one embodiment, the framework layer 820 may be, but is not limited to, a free and open source software network application framework, such as Apache SparkTM (hereinafter referred to as "Spark") that can utilize the distributed file system 828 for large-scale data processing (e.g., "big data"). In at least one embodiment, the job scheduler 832 may include a Spark driver to facilitate scheduling of workloads supported by various layers of the data center 800. In at least one embodiment, the configuration manager 824 may be able to configure different layers, such as the software layer 830 and the framework layer 820 including Spark and a distributed file system 828 for supporting large-scale data processing. In at least one embodiment, the resource manager 826 can manage cluster or group computing resources mapped to or allocated to support the distributed file system 828 and the job scheduler 822. In at least one embodiment, the cluster or group computing resources can include group computing resources 814 on the data center infrastructure layer 810. In at least one embodiment, the resource manager 826 can coordinate with the resource coordinator 812 to manage these mapped or allocated computing resources.

[0071] In at least one embodiment, the software 832 included in the software layer 830 may include software used by at least a portion of the node CRs 816(1)-816(N), the grouped computing resources 814, and / or the distributed file system 828 of the framework layer 820. The one or more types of software may include, but are not limited to, Internet web page search software, email virus scanning software, database software, and streaming video content software.

[0072] In at least one embodiment, one or more applications 842 included in the application layer 840 may include one or more types of applications used by at least a portion of the node CRs 816(1)-816(N), the grouped computing resources 814, and / or the distributed file system 828 of the framework layer 820. The one or more types of applications may include, but are not limited to, any number of genomics applications, cognitive computing, 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 conjunction with one or more embodiments.

[0073] In at least one embodiment, any of the configuration manager 824, resource manager 826, and resource coordinator 812 can implement any number and type of self-modification actions based on any number and type of data acquired in any technically feasible manner. In at least one embodiment, the self-modification actions can relieve a data center operator of the data center 800 from making potentially bad configuration decisions and can avoid underutilized and / or poorly performing portions of the data center.

[0074] In at least one embodiment, the data center 800 may include tools, services, software, or other resources to train one or more machine learning models or use one or more machine learning models to predict or infer information 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 the software and computing resources described above with respect to the data center 800. In at least one embodiment, by using weight parameters calculated by one or more training techniques described herein, information may be inferred or predicted using trained machine learning models corresponding to one or more neural networks using the resources described above with respect to the data center 800.

[0075] In at least one embodiment, the data center can use a CPU, an application-specific integrated circuit (ASIC), a GPU, an FPGA, or other hardware to use the above resources to perform training and / or reasoning. In addition, one or more of the above software and / or hardware resources can be configured as a service to allow users to train or perform information reasoning, such as image recognition, speech recognition, or other artificial intelligence services.

[0076] The reasoning and / or training logic 715 is used to perform reasoning and / or training operations associated with one or more embodiments. In at least one embodiment, the reasoning and / or training logic 715 can be used in the system Figure 8for use in a system for performing inference or prediction 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 described herein.

[0077] Such components can be used to perform enhancements to images using generative diffusion models while maintaining important contextual or semantic content.

[0078] Computer Systems

[0079] Fig. 9 900, which may be a system of interconnected devices and components, a system on a chip (SOC), or some combination thereof formed with a processor that may include an execution unit to execute instructions. In at least one embodiment, in accordance with the present disclosure, such as the embodiments described herein, the computer system 900 may include, but is not limited to, components such as a processor 902, whose execution unit includes logic to execute algorithms for processing data. In at least one embodiment, the computer system 900 may include a processor such as a processor available from Intel Corporation of Santa Clara, California. Processor family, XeonTM, XScaleTM and / or StrongARMTM, Core TM or Nervana TM microprocessor, although other systems (including PCs with other microprocessors, engineering workstations, set-top boxes, etc.) may also be used. In at least one embodiment, computer system 900 may execute a version of the WINDOWS operating system available from Microsoft Corporation of Redmond, Wash., although other operating systems (e.g., UNIX and Linux), embedded software, and / or graphical user interfaces may also be used.

[0080] 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, the embedded application may include a microcontroller, a digital signal processor ("DSP"), a system on a chip, a network computer ("NetPC"), a set-top box, a network hub, a wide area network ("WAN") switch, or any other system that can execute one or more instructions according to at least one embodiment.

[0081] In at least one embodiment, the computer system 900 may include, but is not limited to, a processor 902, which may include, but is not limited to, one or more execution units 908 to perform machine learning model training and / or reasoning according to the techniques described herein. In at least one embodiment, the computer system 900 is a single-processor desktop or server system, but in another embodiment, the computer system 900 may be a multi-processor system. In at least one embodiment, the processor 902 may include, but is not limited to, a complex instruction set computing ("CISC") microprocessor, a reduced instruction set computing ("RISC") microprocessor, a very long instruction word computing ("VLIW") microprocessor, a processor that implements an instruction set combination, or any other processor device, such as a digital signal processor. In at least one embodiment, the processor 902 may be coupled to a processor bus 910, which may transmit data signals between the processor 902 and other components in the computer system 900.

[0082] In at least one embodiment, processor 902 may include, but is not limited to, a level 1 ("L1") internal cache memory ("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 reside external to processor 902. Other embodiments may also include a combination of internal and external caches, depending on the particular implementation and needs. In at least one embodiment, 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.

[0083] In at least one embodiment, one or more execution units 908, including but not limited to logic to perform integer and floating point operations, are also located in the processor 902. In at least one embodiment, the processor 902 may also include a microcode ("ucode") read-only memory ("ROM") for storing microcode for certain macroinstructions. In at least one embodiment, the one or more execution units 908 may include logic for processing a packed instruction set 909. In at least one embodiment, by including the packed instruction set 909 in the instruction set of a general purpose processor, and the associated circuitry to execute the instructions, operations used by many multimedia applications may be performed using packed data in the processor 902. In one or more embodiments, many multimedia applications may be executed faster and more efficiently by using the full width of the processor's data bus to perform operations on packed data, which may not require the transfer of smaller units of data on the processor's data bus to perform one or more operations one data element at a time.

[0084] In at least one embodiment, one or more execution units 908 may also be used in microcontrollers, embedded processors, graphics devices, DSPs, and other types of logic circuits. In at least one embodiment, computer system 900 may include, but is not limited to, 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 other storage device. In at least one embodiment, memory 920 may store instructions 919 and / or data 921 represented by data signals that may be executed by processor 902.

[0085] In at least one embodiment, the system logic chip can be coupled to the processor bus 910 and the memory 920. In at least one embodiment, the system logic chip can include, but is not limited to, a memory controller hub ("MCH") 916, and the processor 902 can communicate with the MCH 916 via the processor bus 910. In at least one embodiment, the MCH 916 can 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 can initiate data signals between the processor 902, the memory 920, and other components in the computer system 900, and bridge data signals between the processor bus 910, the memory 920, and the system I / O 922. In at least one embodiment, the system logic chip can provide a graphics port for coupling to a graphics controller. In at least one embodiment, the MCH 916 can be coupled to the memory 920 via a high-bandwidth memory path 918, and the graphics / video card 912 can be coupled to the MCH 916 via an Accelerated Graphics Port ("AGP") interconnect 914.

[0086] In at least one embodiment, the computer system 900 may use a system I / O 922, which is a proprietary hub interface bus to couple the MCH 916 to an I / O controller hub ("ICH") 930. In at least one embodiment, the ICH 930 may provide direct connections to certain I / O devices through a local I / O bus. In at least one embodiment, the local I / O bus may include, but is not limited to, a high-speed I / O bus used to connect peripheral devices to the memory 920, chipset, and processor 902. Examples may include, but are not limited to, an audio controller 929, a firmware hub ("FlashBIOS") 928, a wireless transceiver 926, a data store 924, a traditional I / O controller 923 including a user input and keyboard interface, a serial expansion port 927 (e.g., a universal serial bus (USB) port), and a network controller 934. The data store 924 may include a hard drive, a floppy drive, a CD-ROM device, a flash memory device, or other mass storage device.

[0087] In at least one embodiment, Fig. 9 The system is shown as comprising interconnected hardware devices or "chips", while in other embodiments, Fig. 9An exemplary system on chip (SoC) may be shown. In at least one embodiment, the devices may be interconnected with a proprietary interconnect, a standardized interconnect (e.g., PCIe), or some combination thereof. In at least one embodiment, one or more components of computer system 900 are interconnected using a compute express link (CXL) interconnect.

[0088] Reasoning and / or training logic 715 is used to perform reasoning and / or training operations related to one or more embodiments. In at least one embodiment, reasoning and / or training logic 715 can be used in Fig. 9 for use in a system for performing inference or prediction 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 described herein.

[0089] Such components can be used to perform enhancements to images using generative diffusion models while maintaining important contextual or semantic content.

[0090] Fig.10 1 is a block diagram illustrating an electronic device 1000 for utilizing a processor 1010 according to at least one embodiment. In at least one embodiment, the electronic device 1000 may be, for example but not limited to, a notebook computer, a tower server, a rack server, a blade server, a laptop computer, a desktop computer, a tablet computer, a mobile device, a phone, an embedded computer, or any other suitable electronic device.

[0091] In at least one embodiment, system 1000 may include, but is not limited to, a processor 1010 communicatively coupled to any suitable number or kind of components, peripherals, modules, or devices. In at least one embodiment, processor 1010 is coupled using a bus or interface, such as an I2C 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 advanced 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 is shown that includes interconnected hardware devices or "chips", while in other embodiments, Fig.10 An exemplary system on chip (SoC) may be shown. In at least one embodiment, Fig.10 The devices shown in can be interconnected with a proprietary interconnect, a standardized interconnect (e.g., PCIe), or some combination thereof. In at least one embodiment, Fig.10 One or more components of the system are interconnected using Compute Express Link (CXL) interconnect lines.

[0092] In at least one embodiment, Fig.10It may include a display 1024, a touch screen 1025, a touch pad 1030, a near field communication unit (“NFC”) 1045, a sensor hub 1040, a thermal sensor 1046, a fast chipset (“EC”) 1035, a trusted platform module (“TPM”) 1038, a BIOS / firmware / flash memory (“BIOS, FWFlash”) 1022, a DSP 1060, a drive 1020 (e.g., a solid state disk (“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 (e.g., a USB 3.0 camera), and / or a low power double data rate (“LPDDR”) memory unit (“LPDDR3”) 1015 implemented with, for example, the LPDDR3 standard. These components may each be implemented in any suitable manner.

[0093] In at least one embodiment, other components may be communicatively coupled to the processor 1010 through the components described above. In at least one embodiment, the accelerometer 1041, ambient light sensor (“ALS”) 1042, compass 1043, and gyroscope 1044 may be communicatively coupled to the sensor hub 1040. In at least one embodiment, the thermal sensor 1039, fan 1037, keyboard 1036, and touchpad 1030 may be communicatively coupled to the EC 1035. In at least one embodiment, the speaker 1063, earphone 1064, and microphone (“mic”) 1065 may be communicatively coupled to the audio unit (“audio codec and class D amplifier”) 1062, which in turn may be communicatively coupled to the DSP 1060. In at least one embodiment, the audio unit 1062 may include, for example, but not limited to, 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 the Bluetooth unit 1052 and the WWAN unit 1056 may be implemented as a next generation form factor (NGFF).

[0094] Reasoning and / or training logic 715 is used to perform reasoning and / or training operations associated with one or more embodiments. In at least one embodiment, reasoning and / or training logic 715 may be used to perform reasoning and / or training operations associated with one or more embodiments. Fig.10 Systems for performing inference or prediction 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 described herein.

[0095] Such components can be used to perform enhancements to images using generative diffusion models while maintaining important contextual or semantic content.

[0096] Fig.11 1100 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 can be a single-processor desktop system, a multi-processor 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 incorporated within a system-on-chip (SoC) integrated circuit for use in a mobile, handheld, or embedded device.

[0097] In at least one embodiment, the processing system 1100 may include or be incorporated into a server-based gaming platform, including a gaming console, a mobile gaming console, a handheld gaming console, or an online gaming console for gaming and media consoles. In at least one embodiment, the processing system 1100 is a mobile phone, a smart phone, a tablet computing device, or a mobile Internet device. In at least one embodiment, the processing system 1100 may also include a wearable device coupled to or integrated in a wearable device, such as a smart watch wearable device, a smart glasses 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.

[0098] In at least one embodiment, 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, each of the one or more processor cores 1107 is configured to process a specific instruction group 1109. In at least one embodiment, the instruction group 1109 can facilitate complex instruction set computing (CISC), reduced instruction set computing (RISC), or calculate by very long instruction words (VLIW). In at least one embodiment, one or more processor cores 1107 can each process different instruction groups 1109, which can include instructions that help emulate other instruction groups. In at least one embodiment, one or more processor cores 1107 can also include other processing devices, such as digital signal processors (DSPs).

[0099] In at least one embodiment, one or more processors 1102 include cache memory 1104. In at least one embodiment, one or more processors 1102 may have a single internal cache or multiple levels of internal cache. In at least one embodiment, the cache memory is shared between various components of one or more processors 1102. In at least one embodiment, one or more processors 1102 also use an external cache (e.g., a level 3 (L3) cache or a last level cache (LLC)) (not shown), which may be shared between one or more processor cores 1107 using known cache coherence techniques. In at least one embodiment, one or more processors 1102 additionally include a register file 1106, and the processor may include different types of registers (e.g., integer registers, floating point registers, status registers, and instruction pointer registers) for storing different types of data. In at least one embodiment, the register file 1106 may include general registers or other registers.

[0100] In at least one embodiment, one or more processors 1102 are coupled to one or more interface buses 1110 to transmit communication signals, such as address, data, or control signals, between one or more processors 1102 and other components in the processing system 1100. In at least one embodiment, the one or more interface buses 1110 may be a processor bus, such as a version of a direct media interface (DMI) bus, in one embodiment. In at least one embodiment, the one or more interface buses 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 1102 includes an integrated memory controller 1116 and a platform controller hub 1130. In at least one embodiment, the memory controller 1116 facilitates communication between memory devices and other components of the processing system 1100, while the platform controller hub (PCH) 1130 provides connections to I / O devices through a local I / O bus.

[0101] In at least one embodiment, the 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 have appropriate performance to be used as a processor memory. In at least one embodiment, the memory device 1120 may be operated as a system memory of the processing system 1100 to store data 1122 and instructions 1121 for use when one or more processors 1102 execute applications or processes. In at least one embodiment, the memory controller 1116 is also coupled to an optional external graphics processor 1112, which may communicate with one or more graphics processors 1108 in the processor 1102 to perform graphics and media operations. In at least one embodiment, a display device 1111 may be connected to the processor 1102. In at least one embodiment, the display device 1111 may include one or more of the internal display devices, such as in a mobile electronic device or 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 used in virtual reality (VR) applications or augmented reality (AR) applications.

[0102] In at least one embodiment, the platform controller hub 1130 allows peripheral devices to be connected to the storage device 1120 and one or more processors 1102 via a high-speed I / O bus. In at least one embodiment, the I / O peripherals include, but are not limited to, an audio controller 1146, a network controller 1134, a firmware interface 1128, a wireless transceiver 1126, a touch sensor 1125, a data storage device 1124 (e.g., a hard drive, flash memory, etc.). In at least one embodiment, the data storage device 1124 can be connected via a storage interface (e.g., SATA) or via a peripheral bus, such as a peripheral component interconnect bus (e.g., PCI, PCIe). In at least one embodiment, the touch sensor 1125 can include a touch screen sensor, a pressure sensor, or a fingerprint sensor. In at least one embodiment, the wireless transceiver 1126 can be a Wi-Fi 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 enables communication with the system firmware and can be, for example, a unified extensible firmware interface (UEFI). In at least one embodiment, the network controller 1134 can enable a network connection to a wired network. In at least one embodiment, a high-performance network controller (not shown) is coupled to the interface bus 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 (e.g., Personal System 2 (PS / 2)) devices to the system 1100. In at least one embodiment, the platform controller hub 1130 can also be connected to one or more universal serial bus (USB) controllers 1142, which connect input devices such as a keyboard and mouse 1143 combination, a camera 1144, or other USB input devices.

[0103] In at least one embodiment, instances of the memory controller 1116 and the 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 the external memory controller 1116 and the platform controller hub 1130, which may be configured as a memory controller hub and a peripheral controller hub in a system chipset that communicates with the processor 1102.

[0104] The reasoning and / or training logic 715 is used to perform reasoning and / or training operations associated with one or more embodiments. In at least one embodiment, some or all of the reasoning and / or training logic 715 can be incorporated into the processing system 1100. For example, in at least one embodiment, the training and / or reasoning techniques described herein can use one or more ALUs that are embodied in a graphics processor. In addition, in at least one embodiment, the reasoning and / or training operations described herein can use a processor other than the ALU. Fig. 7A and / or Figure 7B In at least one embodiment, the weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown) that configure the ALU of the graphics processor to execute one or more of the machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0105] Such components can be used to perform enhancements to images using generative diffusion models while maintaining important contextual or semantic content.

[0106] 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 the additional core 1202N represented by the dashed box. In at least one embodiment, each processor core 1202A-1202N includes one or more internal cache units 1204A-1204N. In at least one embodiment, each processor core may also have access to one or more shared cache units 1206.

[0107] In at least one embodiment, the internal cache units 1204A-1204N and the shared cache unit 1206 represent a cache memory hierarchy within the processor 1200. In at least one embodiment, the cache memory units 1204A-1204N may include at least one level of instruction and data cache within each processor core and one or more levels of cache in a shared mid-level cache, such as level 2 (L2), level 3 (L3), level 4 (L4), or other levels of cache, where the highest level of cache before external memory is categorized as LLC. In at least one embodiment, cache coherence logic maintains coherence between the various cache units 1206 and 1204A-1204N.

[0108] 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, the one or more bus controller units 1216 manage a set of peripheral buses, such as one or more PCI or PCIe buses. In at least one embodiment, the system agent core 1210 provides management functions for various processor components. In at least one embodiment, the system agent core 1210 includes one or more integrated memory controllers 1214 to manage access to various external memory devices (not shown).

[0109] In at least one embodiment, one or more processor cores 1202A-1202N include support for multiple threads simultaneously. 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 for regulating one or more power states of processor cores 1202A-1202N and graphics processor 1208.

[0110] In at least one embodiment, the processor 1200 also includes a graphics processor 1208 for performing graphics processing operations. In at least one embodiment, the graphics processor 1208 is coupled to a shared cache unit 1206 and a system agent core 1210 including one or more integrated memory controllers 1214. In at least one embodiment, the system agent core 1210 also includes a display controller 1211 for driving the graphics processor output to one or more coupled displays. In at least one embodiment, the display controller 1211 may also be a separate module coupled to the graphics processor 1208 via at least one interconnect, or may be integrated within the graphics processor 1208.

[0111] In at least one embodiment, a ring-based interconnect unit 1212 is used to couple the internal components of the processor 1200. In at least one embodiment, alternative interconnect units may be used, such as point-to-point interconnects, switched interconnects, or other technologies. In at least one embodiment, the graphics processor 1208 is coupled to the ring-based interconnect unit 1212 via an I / O link 1213.

[0112] In at least one embodiment, I / O link 1213 represents at least one of a variety of I / O interconnects, including packaged I / O interconnects that facilitate communication between various processor components and high-performance embedded memory modules 1218 (e.g., eDRAM modules). In at least one embodiment, each of processor cores 1202A-1202N and graphics processor 1208 uses embedded memory modules 1218 as a shared last level cache.

[0113] In at least one embodiment, the processor cores 1202A-1202N are homogeneous cores that execute a common instruction set architecture. In at least one embodiment, the processor cores 1202A-1202N are heterogeneous in terms of instruction set architecture (ISA), wherein one or more processor cores 1202A-1202N execute a common instruction set, while one or more other processor cores 1202A-1202N execute a subset or a different instruction set of the common instruction set. In at least one embodiment, the processor cores 1202A-1202N are heterogeneous in terms of microarchitecture, wherein one or more cores with relatively high power consumption are coupled with one or more power cores with lower power consumption. In at least one embodiment, the processor 1200 can be implemented on one or more chips or implemented as a SoC integrated circuit.

[0114] The reasoning and / or training logic 715 is used to perform reasoning and / or training operations associated with one or more embodiments. In at least one embodiment, some or all of the reasoning and / or training logic 715 may be incorporated into the processor 1200. For example, in at least one embodiment, the training and / or reasoning techniques described herein may use one or more ALUs embodied in Fig.12 In addition, in at least one embodiment, the inference and / or training operations described herein may use the inference and / or training operations described herein. Fig. 7A and / or Figure 7B In at least one embodiment, the weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown) that configure the ALU of the graphics processor 1200 to execute one or more of the machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0115] Such components can be used to perform enhancements to images using generative diffusion models while maintaining important contextual or semantic content.

[0116] Virtualized computing platform

[0117] Fig.13is an example data flow diagram of a process 1300 for generating and deploying an image processing and inference pipeline according to at least one embodiment. In at least one embodiment, the process 1300 can be deployed for use with imaging devices, processing devices, and / or other device types at one or more facilities 1302. The process 1300 can be executed within a training system 1304 and / or a deployment system 1306. In at least one embodiment, the training system 1304 can 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 with the deployment system 1306. In at least one embodiment, the deployment system 1306 can be configured to offload processing and computing resources in a distributed computing environment to reduce infrastructure requirements of the facility 1302. In at least one embodiment, one or more applications in the pipeline can use or call services (e.g., reasoning, visualization, computation, AI, etc.) of the deployment system 1306 during application execution.

[0118] In at least one embodiment, some applications used in the high-level processing and reasoning pipeline may use machine learning models or other AI to perform one or more processing steps. In at least one embodiment, the machine learning model may be trained at the facility 1302 using data 1308 (e.g., imaging data) generated at the facility 1302 (and stored on one or more picture archiving and communication system (PACS) servers at the facility 1302), the machine learning model may be trained using imaging or sequencing data 1308 from another one or more facilities, or a combination thereof. In at least one embodiment, the training system 1304 may be used to provide applications, services, and / or other resources to generate a working, deployable machine learning model for the deployment system 1306.

[0119] In at least one embodiment, the model registry 1324 can be backed by an object store, which can support versioning and object metadata. In at least one embodiment, the object store can be accessed from within the cloud platform through, for example, a cloud storage compatible application programming interface (API). In at least one embodiment, the machine learning models within the model registry 1324 can be uploaded, listed, modified, or deleted by developers or partners of the system interacting with the API. In at least one embodiment, the API can provide access to methods that allow users with appropriate credentials to associate a model with an application so that the model can be executed as part of the execution of a containerized instantiation of the application.

[0120] In at least one embodiment, training pipeline 1304 ( Fig.13) may include situations where the facility 1302 is training their 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, a sequencing device, and / or other type of device may be received. In at least one embodiment, once the imaging data 1308 is received, the AI-assisted annotation 1310 may be used to help generate annotations corresponding to the imaging data 1308 to be used as ground truth data for the machine learning model. In at least one embodiment, the AI-assisted annotation 1310 may include one or more machine learning models (e.g., a convolutional neural network (CNN)) that may be trained to generate annotations corresponding to certain types of imaging data 1308 (e.g., from certain devices). In at least one embodiment, the AI-assisted annotation 1310 may then be used directly, or may be adjusted or fine-tuned using an annotation tool to generate ground truth data. In at least one embodiment, the AI-assisted annotation 1310, the labeled data 1312, or a combination thereof may be used as ground truth data for training a machine learning model. In at least one embodiment, the trained machine learning model can be referred to as an output model 1316 and can be used by the deployment system 1306 as described herein.

[0121] In at least one embodiment, the training pipeline may include a scenario where the facility 1302 requires a machine learning model for performing one or more processing tasks for one or more applications in the deployment system 1306, but the facility 1302 may not currently have such a machine learning model (or may not have a model that is optimized, efficient, or effective for this purpose). In at least one embodiment, an existing machine learning model may be selected from the model registry 1324. In at least one embodiment, the model registry 1324 may include machine learning models that are trained to perform a variety of different reasoning tasks on imaging data. In at least one embodiment, the machine learning models in the model registry 1324 may be trained on imaging data from a different facility (e.g., a facility located far away) rather than the facility 1302. In at least one embodiment, the machine learning model may have been trained on imaging data from one location, two locations, or any number of locations. In at least one embodiment, when training is performed on imaging data from a specific location, the training may be performed at that location, or at least in a manner that protects the confidentiality of the imaging data or restricts the transfer of the imaging data from off-site. In at least one embodiment, once a model is trained or partially trained at one location, the machine learning model can be added to the model registry 1324. In at least one embodiment, the machine learning model can then be retrained or updated at any number of other facilities, and the retrained or updated model can be used in the model registry 1324. In at least one embodiment, the machine learning model can then be selected from the model registry 1324 (and referred to as the output model 1316) and can be deployed in the deployment system 1306 to perform one or more processing tasks for one or more applications of the deployment system.

[0122] In at least one embodiment, the scenario may include a facility 1302 that requires a machine learning model for performing one or more processing tasks for one or more applications in the deployment system 1306, but the facility 1302 may not currently have such a machine learning model (or may not have an optimized, efficient, or effective model). In at least one embodiment, the machine learning model selected from the model registry 1324 may not be fine-tuned or optimized for the imaging data 1308 generated at the facility 1302 due to population differences, robustness of the training data used to train the machine learning model, diversity of training data anomalies, and / or other issues with the training data. In at least one embodiment, AI-assisted annotations 1310 can be used to help generate annotations corresponding to the imaging data 1308 for use as ground truth data for training or updating the machine learning model. In at least one embodiment, labeled clinical data 1312 can be used as ground truth data for training the machine learning model. In at least one embodiment, retraining or updating the machine learning model can be referred to as model training 1314. In at least one embodiment, model training 1314 (e.g., AI-assisted annotations 1310, labeled data 1312, or a combination thereof) can be used as ground truth data to retrain or update a machine learning model. In at least one embodiment, the trained machine learning model can be referred to as an output model 1316 and can be used by the deployment system 1306, as described herein.

[0123] In at least one embodiment, the deployment system 1306 may include software 1318, services 1320, hardware 1322, and / or other components, features, and functions. In at least one embodiment, the deployment system 1306 may include a software "stack" such that the software 1318 may be built on top of the services 1320 and may use the services 1320 to perform some or all of the processing tasks, and the services 1320 and software 1318 may be built on top of the hardware 1322 and use the hardware 1322 to perform the processing, storage, and / or other computing tasks of the deployment system. In at least one embodiment, the software 1318 may include any number of different containers, each of which may perform an instantiation of an application. In at least one embodiment, each application may perform one or more processing tasks (e.g., reasoning, object detection, feature detection, segmentation, image enhancement, calibration, etc.) in a high-level processing and reasoning pipeline. In at least one embodiment, in addition to receiving and configuring imaging data for use by each container and / or containers used by facility 1302 after processing through the pipeline, a high-level processing and reasoning pipeline can also be defined based on the selection of different containers desired or required to process imaging data 1308 (e.g., to convert the output back into a usable data type. In at least one embodiment, the combination of containers within software 1318 (e.g., which constitute a pipeline) can be referred to as a virtual instrument (as described in more detail herein), and the virtual instrument can utilize services 1320 and hardware 1322 to perform some or all of the processing tasks of an application instantiated in a container.

[0124] In at least one embodiment, the data processing pipeline can 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 the deployment system 1306). In at least one embodiment, the input data can represent one or more images, videos, and / or other data representations generated by one or more imaging devices. In at least one embodiment, the data can be pre-processed 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 can be performed on the output of one or more inference tasks or other processing tasks of the pipeline to prepare output data for the next application and / or prepare the output data for transmission and / or use by the user (e.g., as a response to the inference request). In at least one embodiment, the inference task can be performed by one or more machine learning models, such as a trained or deployed neural network, which can include the output model 1316 of the training system 1304.

[0125] In at least one embodiment, tasks of a data processing pipeline may be encapsulated in containers, each container representing a discrete, fully functional instantiation of an application and a virtualized computing environment capable of referencing a machine learning model. In at least one embodiment, containers or applications may be published to a private (e.g., limited access) area of ​​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, an image of an application (e.g., a container image) may be available in a container registry, and once a user selects an image from a container registry for deployment in a pipeline, the image may be used to generate an instantiated container for the application for use by the user's system.

[0126] In at least one embodiment, a developer (e.g., a software developer, a clinician, a physician, etc.) can develop, publish, and store applications (e.g., as containers) for performing image processing and / or reasoning on provided data. In at least one embodiment, the development, publishing, and / or storage can be performed using a software development kit (SDK) associated with the system (e.g., to ensure that the developed applications and / or containers conform to or are compatible with the system). In at least one embodiment, the developed applications can be tested locally (e.g., at a first facility, on data from the first facility) using the SDK, which is installed as part of the system (e.g., Fig.12 Processor 1200 in the process 1300) may support at least some services 1320. In at least one embodiment, because a DICOM object may contain from one to hundreds of images or other data types, and because the data varies, the developer may be responsible for managing (e.g., setting up constructs for building pre-processing into the application, etc.) the extraction and preparation of the incoming data. In at least one embodiment, once validated by process 1300 (e.g., for accuracy), the application is made available in the container registry for selection and / or implementation by the user to perform one or more processing tasks on the data at the user's facility (e.g., a second facility).

[0127] In at least one embodiment, the developer can then share the application or container over a network for use by a system (e.g., Fig.131300). In at least one embodiment, the completed and validated application or container can be stored in the container registry, and the associated machine learning model can be stored in the model registry 1324. In at least one embodiment, the requesting entity (which provides the reasoning or image processing request) can browse the container registry and / or the model registry 1324 to obtain applications, containers, data sets, machine learning models, etc., select the desired combination of elements to be included in the data processing pipeline, and submit the image processing request. In at least one embodiment, the request may include the input data necessary to execute the request (and in some examples, patient-related data), and / or may include a selection of applications and / or machine learning models to be executed when processing the request. In at least one embodiment, the request can then be passed to one or more components (e.g., a cloud) of the deployment system 1306 to perform processing of the data processing pipeline. In at least one embodiment, the processing performed by the deployment system 1306 may include referencing elements (e.g., applications, containers, models, etc.) selected from the container registry and / or the model registry 1324. In at least one embodiment, once the results are generated by the pipeline, the results may be returned to the user for reference (eg, for viewing in a viewing application suite executing locally, on a local workstation or terminal).

[0128] In at least one embodiment, to assist in processing or executing applications or containers in the pipeline, services 1320 may be utilized. In at least one embodiment, services 1320 may include computing 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, and thus may abstract functionality into services that may be called or utilized by applications. In at least one embodiment, the functionality provided by services 1320 may run dynamically and more efficiently, while also allowing applications to process data in parallel (e.g., using Fig.12In at least one embodiment, rather than requiring that each application that shares the same functionality provided by the service 1320 must have a corresponding instance of the service 1320, the service 1320 can be shared between and among various applications. In at least one embodiment, as a non-limiting example, the service may include an inference server or engine that can be used to perform detection or segmentation tasks. In at least one embodiment, a model training service may be included that can provide machine learning model training and / or retraining capabilities. In at least one embodiment, a data enhancement service may be further included that can provide GPU-accelerated data (e.g., DICOM, RIS, CIS, REST-compliant, RPC, raw, etc.) extraction, resizing, scaling, and / or other enhancements. In at least one embodiment, a visualization service may be used that can add image rendering effects (e.g., ray tracing, rasterization, denoising, sharpening, etc.) to add realism to two-dimensional (2D) and / or three-dimensional (3D) models. In at least one embodiment, a virtual instrument service may be included that provides beamforming, segmentation, reasoning, imaging, and / or support for other applications within the pipeline of the virtual instrument.

[0129] In at least one embodiment, where the service 1320 includes an AI service (e.g., an inference service), as part of the execution of an application, one or more machine learning models can be executed by calling (e.g., as an API call) an inference service (e.g., an inference server) to execute one or more machine learning models or processing thereof. In at least one embodiment, where another application includes one or more machine learning models for a segmentation task, the application can call the inference service to execute the machine learning model for performing one or more processing operations associated with the segmentation task. In at least one embodiment, the software 1318 implementing the high-level processing and inference pipeline, which includes a segmentation application and anomaly detection application, can be pipelined because each application can call the same inference service to perform one or more inference tasks.

[0130] In at least one embodiment, the hardware 1322 may include a GPU, a CPU, a graphics card, 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, purpose-built support for the software 1318 and services 1320 in the deployment system 1306. In at least one embodiment, the use of GPU processing may be implemented to perform local processing (e.g., at the facility 1302) within the AI / deep learning system, in the cloud system, and / or 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, as a non-limiting example, with respect to deep learning, machine learning, and / or high-performance computing, the software 1318 and / or services 1320 may be optimized for GPU processing. In at least one embodiment, at least some of the computing environments of the deployment system 1306 and / or training system 1304 may be executed in a data center, one or more supercomputers, or high-performance computer systems with GPU-optimized software (e.g., a combination of hardware and software of an NVIDIA DGX system). In at least one embodiment, as described herein, hardware 1322 may include any number of GPUs that may be called to perform data processing in parallel. In at least one embodiment, the cloud platform may also include GPU optimized execution for deep learning tasks, GPU processing for machine learning tasks or other computing tasks. In at least one embodiment, an AI / deep learning supercomputer and / or GPU optimized software (e.g., as provided on NVIDIA's DGX system) may be used as a hardware abstraction and scaling platform to execute a cloud platform (e.g., NVIDIA's NGC). In at least one embodiment, the cloud platform may integrate an application container cluster system or coordination system (e.g., Kubernetes) on multiple GPUs to allow seamless scaling and load balancing.

[0131] Fig.14 is a system diagram of an example system 1400 for generating and deploying an imaging deployment pipeline according to at least one embodiment. In at least one embodiment, the system 1400 can be used to implement Fig.13 The process 1300 and / or other processes of the system 1400 may include a high-level processing and reasoning pipeline. In at least one embodiment, the system 1400 may include a training system 1304 and a deployment system 1306. In at least one embodiment, the training system 1304 and the deployment system 1306 may be implemented using software 1318, services 1320, and / or hardware 1322, as described herein.

[0132] In at least one embodiment, system 1400 (e.g., training system 1304 and / or deployment system 1306) can be implemented in a cloud computing environment (e.g., using cloud 1426). In at least one embodiment, system 1400 can be implemented locally (with respect to a healthcare service facility) or as a combination of cloud computing resources and local computing resources. In at least one embodiment, access to APIs in cloud 1426 can be restricted to authorized users by establishing security measures or protocols. In at least one embodiment, the security protocol can include a network token, which can be signed by an authentication (e.g., AuthN, AuthZ, Gluecon, etc.) service and can carry appropriate authorization. In at least one embodiment, the API of the virtual instrument (described herein) or other instances of system 1400 can be restricted to a set of public IPs that have been audited or authorized for interaction.

[0133] In at least one embodiment, the various components of system 1400 can communicate with each other using any of a variety of different 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 facilities and components of system 1400 (e.g., for sending inference requests, for receiving results of inference requests, etc.) can be transmitted via one or more data buses, wireless data protocols (Wi-Fi), wired data protocols (e.g., Ethernet), etc.

[0134] In at least one embodiment, similar to the present disclosure regarding Fig.13 As described, the training system 1304 can execute the training pipeline 1404. In at least one embodiment, where the deployment system 1306 will use one or more machine learning models in the deployment pipeline 1410, the training pipeline 1404 can be used to train or retrain one or more (e.g., pre-trained) models, and / or implement one or more pre-trained models 1406 (e.g., without retraining or updating). In at least one embodiment, as a result of the training pipeline 1404, an output model 1316 can be generated. In at least one embodiment, the training pipeline 1404 can 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 pipelines 1404 can be used for different machine learning models used by the deployment system 1306. In at least one embodiment, similar to the description regarding Fig.13 The first example training pipeline 1404 described may be used for a first machine learning model, similar to the training pipeline 1404 described with respect to FIG. Fig.13 The second example training pipeline 1404 described may be used for a second machine learning model, similar to the one described with respect to Fig.13The training pipeline 1404 of the third example described may be used for a third machine learning model. In at least one embodiment, any combination of tasks within the training system 1304 may be used according to the requirements of each corresponding machine learning model. In at least one embodiment, one or more machine learning models may have been trained and ready for deployment, so the training system 1304 may not perform any processing on the machine learning model, and one or more machine learning models may be implemented by the deployment system 1306.

[0135] In at least one embodiment, the output model 1316 and / or the pre-trained model 1406 may include any type of machine learning model, depending on the implementation or embodiment. In at least one embodiment and without limitation, the machine learning model used by the system 1400 may include using linear regression, logistic regression, decision tree, support vector machine (SVM), naive Bayes, k-nearest neighbor (Knn), k-means clustering, random forest, dimensionality reduction algorithm, gradient boosting algorithm, neural network (e.g., autoencoder, convolution, recursion, perceptron, long / short term memory (LSTM), Hopfield, Boltzmann, deep belief, deconvolution, generative adversarial, liquid state machine, etc.), and / or other types of machine learning models.

[0136] In at least one embodiment, the training pipeline 1404 may include AI-assisted annotation, as described herein with respect to at least Fig.14In more detail. In at least one embodiment, the labeled clinical data 1312 (e.g., traditional annotations) can be generated by any number of techniques. In at least one embodiment, in some examples, labels or other annotations can be generated in a drawing program (e.g., an annotation program), a computer-aided design (CAD) program, a labeling program, another type of application suitable for generating ground-truth annotations or labels, and / or can be hand-drawn. In at least one embodiment, the ground-truth data can be synthetically generated (e.g., generated from a computer model or rendering), truly generated (e.g., designed and generated from real-world data), machine-generated (e.g., using feature analysis and learning to extract features from the data and then generate labels), manually annotated (e.g., a labeler or annotation expert, defining the location of the label), and / or a combination thereof. In at least one embodiment, for each instance of imaging data 1308 (or other data types used by machine learning models), there can be corresponding ground-truth data generated by the training system 1304. In at least one embodiment, AI-assisted annotation 1310 can be performed as part of a deployment pipeline 1410; supplementing or replacing the AI-assisted annotation 1310 included in the training pipeline 1404. In at least one embodiment, the system 1400 may include a multi-layer platform that may include a software layer (e.g., software 1318) of a diagnostic application (or other application type) that may perform one or more medical imaging and diagnostic functions. In at least one embodiment, the system 1400 may be communicatively coupled (e.g., via an encrypted link) to a PACS server network of one or more facilities. In at least one embodiment, the system 1400 may be configured to access and reference data from a PACS server to perform operations such as training a machine learning model, deploying a machine learning model, image processing, reasoning, and / or other operations.

[0137] In at least one embodiment, the software layer may be implemented as a secure, encrypted, and / or authenticated API through which an application or container may be invoked (e.g., called) from an external environment (e.g., facility 1302). In at least one embodiment, the application may then call or execute one or more services 1320 to perform computational, AI, or visualization tasks associated with the respective application, and the 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 received by or sent to the training system 1304 and deployment system 1306 may occur using a pair of DICOM adapters 1402A, 1402B.

[0138] In at least one embodiment, the deployment system 1306 can execute a deployment pipeline 1410. In at least one embodiment, the deployment pipeline 1410 can include any number of applications, which can be sequential, non-sequential, or otherwise applied to imaging data (and / or other data types) - including AI-assisted annotations, generated by imaging devices, sequencing devices, genomics devices, etc., as described above. In at least one embodiment, as described herein, the deployment pipeline 1410 for an individual device can be referred to as a virtual instrument for the device (e.g., a virtual ultrasound instrument, a virtual CT scanning instrument, a virtual sequencing instrument, etc.). In at least one embodiment, there can be more than one deployment pipeline 1410 for a single device, depending on the information desired from the data generated by the device. In at least one embodiment, there can be a first deployment pipeline 1410 in the case where an abnormality is desired to be detected from an MRI machine, and there can be a second deployment pipeline 1410 in the case where image enhancement is desired from the output of the MRI machine.

[0139] In at least one embodiment, the 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 the model registry 1324. In at least one embodiment, a user may implement their own machine learning model or select a machine learning model to be included in an application that performs a processing task. In at least one embodiment, the application may be selectable and customizable, and by defining the construction of the application, the deployment and implementation of the application for a particular user is presented as a more seamless user experience. In at least one embodiment, by leveraging other features of the system 1400 (e.g., services 1320 and hardware 1322), the deployment pipeline 1410 may be more user-friendly, provide easier integration, and produce more accurate, efficient, and timely results.

[0140] In at least one embodiment, the deployment system 1306 may include a user interface 1414 (e.g., a graphical user interface, a web interface, etc.) that may be used to select applications to be included in the deployment pipeline 1410, to arrange applications, to modify or change applications or their parameters or configurations, to use and interact with the deployment pipeline 1410 during setup and / or deployment, and / or to otherwise interact with the deployment system 1306. In at least one embodiment, although not shown with respect to the training system 1304, the UI 1414 (or a different user interface) may be used to select models for use in the deployment system 1306, to select models for training or retraining in the training system 1304, and / or to otherwise interact with the training system 1304.

[0141] In at least one embodiment, in addition to the application coordination system 1428, a pipeline manager 1412 may be used to manage the interaction between the application or container of the deployment pipeline 1410 and the service 1320 and / or the hardware 1322. In at least one embodiment, the pipeline manager 1412 may be configured to facilitate the interaction from application to application, from application to service 1320, and / or from application or service to hardware 1322. In at least one embodiment, although shown as included in the software 1318, this is not intended to be limiting, and in some examples, the pipeline manager 1412 may be included in the service 1320. In at least one embodiment, the application coordination system 1428 (e.g., Kubernetes, DOCKER, etc.) may include a container coordination system that can group applications into containers as a logical unit for coordination, management, scaling, and deployment. In at least one embodiment, by associating applications from the deployment pipeline 1410 (e.g., rebuilding applications, splitting applications, etc.) with individual containers, each application can be executed in a self-contained environment (e.g., at the kernel level) to improve speed and efficiency.

[0142] In at least one embodiment, each application and / or container (or its image) can be developed, modified, and deployed separately (e.g., a first user or developer can develop, modify, and deploy a first application, and a second user or developer can develop, modify, and deploy a second application separate from the first user or developer), which can allow for focus and attention on the tasks of a single application and / or container without being hindered by the tasks of another application or container. In at least one embodiment, the pipeline manager 1412 and the application coordination system 1428 can assist in communication and collaboration between different containers or applications. In at least one embodiment, as long as the expected inputs and / or outputs of each container or application are known to the system (e.g., based on the construction of the application or container), the application coordination system 1428 and / or the pipeline manager 1412 can facilitate communication and sharing of resources between and among each application or container. In at least one embodiment, since one or more applications or containers in the deployment pipeline 1410 can share the same services and resources, the application coordination system 1428 can coordinate, load balance, and determine the sharing of services or resources between and among the various applications or containers. In at least one embodiment, the scheduler can be used to track resource requirements of applications or containers, current or planned use of those resources, and resource availability. Thus, in at least one embodiment, the scheduler can allocate resources to different applications and allocate resources between and among applications, taking into account the needs and availability of the system. In some examples, the scheduler (and / or other components of the application coordination system 1428) can determine resource availability and distribution based on constraints imposed on the system (e.g., user constraints), such as quality of service (QoS), the urgency of data output (e.g., to determine whether to perform real-time processing or delayed processing), etc.

[0143] In at least one embodiment, the services 1320 utilized and shared by the applications or containers in the deployment system 1306 may include computing services 1416, AI services 1418, visualization services 1420, and / or other service types. In at least one embodiment, an application may call (e.g., execute) one or more services 1320 to perform processing operations for the application. In at least one embodiment, an application may utilize computing services 1416 to perform supercomputing or other high performance computing (HPC) tasks. In at least one embodiment, one or more computing services 1416 may be utilized to perform parallel processing (e.g., using a parallel computing platform 1430) to process data substantially simultaneously by one or more applications and / or one or more tasks of a single application. In at least one embodiment, a parallel computing platform 1430 (e.g., NVIDIA's CUDA) may implement general computing on a GPU (GPGPU) (e.g., GPU / graphics 1422). In at least one embodiment, the software layer of the parallel computing platform 1430 may provide access to a virtual instruction set and parallel computing elements of a GPU to execute computing 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, inter-process communication (IPC) calls may be generated for multiple containers and / or multiple processes within a container to enable the same data (e.g., where multiple different stages of an application or multiple applications are processing the same information) to be used for a shared memory segment from the parallel computing platform 1430. In at least one embodiment, instead of copying data and moving the data to different locations in memory (e.g., read / write operations), the same data in the same location of the memory may be used for any number of processing tasks (e.g., at the same time, at different times, etc.). In at least one embodiment, since the data as a result of processing is used to generate new data, this information of the new location of the data may be stored and shared between various applications. In at least one embodiment, the location of the data and the location of the updated or modified data may be part of the definition of how to understand the payload in the container.

[0144] In at least one embodiment, the AI ​​service 1418 may be utilized to perform a reasoning service for executing a machine learning model associated with an application (e.g., a task is to execute one or more processing tasks of an application). In at least one embodiment, the AI ​​service 1418 may utilize the AI ​​system 1424 to execute a machine learning model (e.g., a neural network such as a CNN) for segmentation, reconstruction, object detection, feature detection, classification, and / or other reasoning tasks. In at least one embodiment, the application of the deployment pipeline 1410 may use one or more output models 1316 of the self-training system 1304 and / or other models of the application to perform reasoning on the imaging data. In at least one embodiment, two or more examples of reasoning using the application coordination system 1428 (e.g., a scheduler) may be available. In at least one embodiment, the first category may include a high priority / low latency path that can achieve a higher service level agreement, such as for performing reasoning on an urgent request in an emergency, or for a radiologist during a diagnostic process. In at least one embodiment, the second category may include a standard priority path that may be used for requests that may not be urgent or where analysis can be performed at a later time. In at least one embodiment, application coordination system 1428 can allocate resources (e.g., services 1320 and / or hardware 1322) for different reasoning tasks of AI service 1418 based on priority paths.

[0145] In at least one embodiment, the shared memory may be installed to the AI ​​service 1418 in the system 1400. In at least one embodiment, the shared memory may operate as a cache (or other storage device type) and may be used to process inference requests from applications. In at least one embodiment, when an inference request is submitted, a set of API instances of the deployment system 1306 may receive the request and may select one or more instances (e.g., for best fit, for load balancing, etc.) to process the request. In at least one embodiment, in order to process the request, the request may be entered into a database, and if it is not already in the cache, the machine learning model may be located from the model registry 1324, a verification step may ensure that the appropriate machine learning model is loaded into the cache (e.g., shared storage), and / or a copy of the model may be saved to the cache. In at least one embodiment, if the application is not yet running or there are not enough instances of the application, a scheduler (e.g., a scheduler of the pipeline manager 1412) may be used to start the application referenced in the request. In at least one embodiment, if the inference server has not yet been started to execute the model, the inference server may be started. Any number of inference servers may be started for each model. In at least one embodiment, in a pull model that clusters inference servers, the model can be cached whenever load balancing is beneficial. In at least one embodiment, the inference servers can be statically loaded into the corresponding distributed servers.

[0146] In at least one embodiment, inference can be performed using an inference server running in a container. In at least one embodiment, an instance of an inference server can be associated with a model (and optionally with multiple versions of a model). In at least one embodiment, if an instance of an inference server does not exist when a request is received to perform inference on a model, a new instance can be loaded. In at least one embodiment, when the inference server is started, the model can be passed to the inference server so that the same container can be used to serve different models as long as the inference server is running as a different instance.

[0147] In at least one embodiment, during application execution, a request for reasoning for a given application may be received, and a container (e.g., an instance of a hosted reasoning server) may be loaded (if not already loaded), and a launcher may be called. In at least one embodiment, preprocessing logic in the container may load, decode, and / or perform any additional preprocessing on the incoming data (e.g., using a CPU and / or GPU). In at least one embodiment, once the data is ready for reasoning, the container may perform reasoning on the data as needed. In at least one embodiment, this may include a single reasoning call for one image (e.g., a hand X-ray), or may require reasoning for hundreds of images (e.g., a chest CT). In at least one embodiment, the application may summarize the results before completion, which may include, but is not limited to, a single confidence score, pixel-level segmentation, voxel-level segmentation, generating visualizations, or generating text to summarize the results. In at least one embodiment, different priorities may be assigned to different models or applications. For example, some models may have a real-time (TAT less than 1 minute) priority, while other models may have a lower priority (e.g., TAT less than 10 minutes). In at least one embodiment, model execution time may be measured from a requesting mechanism or entity and may include collaborative network traversal time as well as execution time of an inference service.

[0148] In at least one embodiment, the transmission of requests between the service 1320 and the reasoning application can be hidden behind a software development kit (SDK), and robust transmission can be provided through queues. In at least one embodiment, requests will be placed in queues through an API for individual application / tenant ID combinations, and the SDK will pull requests from the queue and provide the request to the application. In at least one embodiment, the name of the queue can be provided in the environment from which the SDK will pick up the queue. In at least one embodiment, asynchronous communication through queues may be useful because it can allow any instance of the application to pick up work when it is available. Results can be transmitted back through the queue to ensure that no data is lost. In at least one embodiment, the queue can also provide the ability to split the work, because the highest priority work can enter the queue connected to most instances of the application, and the lowest priority work can enter the queue connected to a single instance, which processes the tasks in the order received. In at least one embodiment, the application can run on a GPU-accelerated instance generated in the cloud 1426, and the reasoning service can perform reasoning on the GPU.

[0149] In at least one embodiment, visualization services 1420 may be utilized to generate visualizations for viewing application and / or deployment pipeline 1410 outputs. In at least one embodiment, visualization services 1420 may utilize GPU / graphics 1422 to generate visualizations. In at least one embodiment, visualization services 1420 may implement rendering effects such as ray tracing to generate higher quality visualizations. In at least one embodiment, visualizations may include, but are not limited to, 2D image rendering, 3D volume rendering, 3D volume reconstruction, 2D tomographic slices, virtual reality displays, augmented reality displays, and the like. In at least one embodiment, a virtualized environment may be used to generate a virtual interactive display or environment (e.g., a virtual environment) for system users (e.g., doctors, nurses, radiologists, etc.) to interact with. In at least one embodiment, visualization services 1420 may include internal visualizers, movies, and / or other rendering or image processing capabilities or functions (e.g., ray tracing, rasterization, internal optics, etc.).

[0150] In at least one embodiment, hardware 1322 may include GPU / graphics 1422, AI system 1424, cloud 1426, and / or any other hardware for executing training system 1304 and / or deployment system 1306. In at least one embodiment, GPU / graphics 1422 (e.g., NVIDIA's TESLA and / or QUADRO GPUs) may include any number of GPUs that may be used to perform processing tasks for any feature or functionality of compute services 1416, AI services 1418, visualization services 1420, other services, and / or software 1318. For example, for AI services 1418, GPU / graphics 1422 may be used to perform pre-processing on imaging data (or other data types used by machine learning models), post-processing on the output of machine learning models, and / or perform inference (e.g., to execute machine learning models). In at least one embodiment, cloud 1426, AI system 1424, and / or other components of system 1400 may use GPU / graphics 1422. 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 use a GPU, and cloud 1426 (or at least part of a task being deep learning or reasoning) may be executed using one or more AI systems 1424. Likewise, while hardware 1322 is shown as discrete components, this is not intended to be limiting, and any component of hardware 1322 may be combined with or utilized by any other component of hardware 1322.

[0151] In at least one embodiment, AI system 1424 may include a purpose-built computing system (e.g., a supercomputer or HPC) configured for reasoning, deep learning, machine learning, and / or other artificial intelligence tasks. In at least one embodiment, in addition to CPU, RAM, storage, and / or other components, features, or functions, AI system 1424 (e.g., NVIDIA's DGX) may also include software (e.g., a software stack) that can use multiple GPUs / graphics 1422 to perform GPU-optimized tasks. In at least one embodiment, one or more AI systems 1424 may be implemented in a cloud 1426 (e.g., in a data center) to perform some or all of the AI-based processing tasks of system 1400.

[0152] In at least one embodiment, cloud 1426 may include a GPU-accelerated infrastructure (e.g., NVIDIA's NGC) that 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 executing 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 with an application coordination system 1428 that utilizes multiple GPUs to enable seamless scaling and load balancing between and among applications and services 1320. In at least one embodiment, cloud 1426 may be responsible for executing at least some services 1320 of system 1400, including compute services 1416, AI services 1418, and / or visualization services 1420, as described herein. In at least one embodiment, cloud 1426 can perform large and small batch inference (e.g., executing NVIDIA's TENSOR RT), provide a parallel computing platform 1430 (e.g., NVIDIA's CUDA), execute an application coordination 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 to produce higher quality movie effects), and / or can provide other functionality for system 1400.

[0153] Fig.15A A data flow diagram of a process 1500 for training, retraining, or updating a machine learning model according to at least one embodiment is shown. In at least one embodiment, a non-limiting example may be used. Fig.14 The process 1500 may be performed by the system 1400 of FIG. 1400. In at least one embodiment, the process 1500 may utilize the service 1320 and / or the hardware 1322 as described herein. In at least one embodiment, the refined model 1512 generated by the process 1500 may be executed by the deployment system for one or more containerized applications in a deployment pipeline.

[0154] 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 customer data set 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, the output or loss layer of the initial model 1504 may be reset or deleted, and / or replaced with an updated or new output or loss layer. In at least one embodiment, the initial model 1504 may have previously fine-tuned parameters (e.g., weights and / or biases) retained from previous training, so training or retraining may not take as long or require as much processing as training the model from scratch. In at least one embodiment, during model training 1514, by resetting or replacing the output or loss layer of the initial model 1504, when generating predictions on the new customer data set 1506, the parameters for the new data set may be updated and re-adjusted based on the loss calculation associated with the accuracy of the output or loss layer.

[0155] In at least one embodiment, the pre-trained model 1506 may be stored in a data store or registry. In at least one embodiment, the pre-trained model 1506 may have been trained at least in part at one or more facilities other than the facility performing process 1500. In at least one embodiment, in order to protect the privacy and rights of patients, subjects, or customers of different facilities, the pre-trained model 1506 may have been trained locally using locally generated customer or patient data. In at least one embodiment, the cloud and / or other hardware may be used to train the pre-trained model 1506, but confidential, privacy-protected patient data may not be transmitted to any component of the cloud (or other non-local hardware), used by it, or accessed by it. In at least one embodiment, if the pre-trained model 1506 is trained using patient data from more than one facility, the pre-trained model 1506 may have been trained separately for each facility before training on patient or customer data from another facility. In at least one embodiment, for example where customer or patient data has been issued privacy issues (e.g., by being waived, used for experimental purposes, etc.), or where the customer or patient data is included in a public dataset, customer or patient data from any number of facilities can be used to train pre-trained model 1506 locally and / or externally, such as in a data center or other cloud computing infrastructure.

[0156] In at least one embodiment, when selecting an application to use in a deployment pipeline, the user may also select a machine learning model to use for a particular application. In at least one embodiment, the user may not have a model to use, so the user may select a pre-trained model 1506 to use with the application. In at least one embodiment, the pre-trained model may not be optimized to generate accurate results on the customer data set of the user facility (e.g., based on patient diversity, demographics, type of medical imaging equipment used, etc.). In at least one embodiment, the pre-trained model 1506 may be updated, retrained, and / or fine-tuned for use at various facilities before deploying the pre-trained model 1506 into a deployment pipeline for use with one or more applications.

[0157] In at least one embodiment, a user may select a pre-trained model 1506 to be updated, retrained, and / or fine-tuned, and the pre-trained model may be referred to as the initial model 1504 for training the system in process 1500. In at least one embodiment, a customer data set 1506 (e.g., imaging data, genomic data, sequencing data, or other data types generated by equipment 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 a 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 1304. In at least one embodiment, the ground truth data may be generated, at least in part, at the facility by a clinician, scientist, physician, practitioner.

[0158] 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 utilize a machine learning model (e.g., a neural network) to generate ground truth data for recommendations or predictions for a customer data set. In at least one embodiment, a user may use the annotation tool within a user interface (graphical user interface (GUI)) on a computing device.

[0159] In at least one embodiment, user 1510 can interact with the GUI via computing device 1508 to edit or fine-tune annotations or automatic annotations. In at least one embodiment, a polygon editing feature can be used to move vertices of a polygon to a more precise or fine-tuned position.

[0160] In at least one embodiment, once the customer dataset 1506 has associated ground truth data, the ground truth data (e.g., from AI-assisted annotations, manual labeling, etc.) can be used during model training to generate a refined model 1512. In at least one embodiment, the customer dataset 1506 can be applied to the initial model 1504 any number of times, and the ground truth data can be used to update the parameters of the initial model 1504 until an acceptable level of accuracy is achieved for the refined model 1512. In at least one embodiment, once the refined model 1512 is generated, the refined model 1512 can be deployed within one or more deployment pipelines at a facility for use in performing one or more processing tasks with respect to medical imaging data.

[0161] In at least one embodiment, the refined model 1512 can be uploaded to the pre-trained models 1542 in the model registry to be selected by another facility. In at least one embodiment, this process can be completed at any number of facilities, so that the refined model 1512 can be further refined any number of times on new data sets to generate a more general model.

[0162] Fig. 15B is an example illustration of a client-server architecture 1532 for enhancing an annotation tool with a pre-trained model 1542 according to at least one embodiment. In at least one embodiment, an AI-assisted annotation tool 1536 can be instantiated based on the client-server architecture 1532. In at least one embodiment, the AI-assisted annotation tool 1536 in an imaging application can assist radiology physicians, such as identifying organs and abnormalities. In at least one embodiment, the imaging application can include a software tool that, as a non-limiting example, helps a user 1510 identify several extreme points on a specific organ of interest in an original image 1534 (e.g., in a 3D MRI or CT scan) and receive automatic annotation results for all 2D slices of the specific organ. In at least one embodiment, the results can be stored in a data store as training data 1538 and used as, for example, but not limited to, ground truth data for training. In at least one embodiment, when the computing device 1508 sends extreme points for AI-assisted annotation, for example, a deep learning model can receive the data as input and return an inference result for segmenting an organ or anomaly. In at least one embodiment, the pre-instantiated annotation tool (e.g., Fig. 15BThe AI-assisted annotation tool 1536 in the example may be enhanced by making an API call (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 in, for example, an annotation model registry. In at least one embodiment, the annotation model registry may store pre-trained models 1542 (e.g., machine learning models, such as deep learning models) that are pre-trained to perform AI-assisted annotation 1310 on specific organs or abnormalities. In at least one embodiment, these models can be further updated by using a training pipeline. In at least one embodiment, the pre-installed annotation tools can be improved over time as newly labeled data is added.

[0163] Various embodiments may be described by the following terms:

[0164] 1. A computer-implemented method comprising:

[0165] removing text from the object represented in the first image;

[0166] providing the first image of the object without the removed text as input to a generative diffusion model;

[0167] receiving a second image of the object as an output of generating a diffusion model, the second image comprising one or more annotations of the object; and

[0168] The text is blended into the second image of the object such that the one or more annotations are represented as being applied to the object and the text in the second image.

[0169] 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 the representation of the object in the second image.

[0170] 3. The computer-implemented method of clause 1, further comprising:

[0171] A textual cue is provided as an additional input to the generative diffusion model, the textual cue indicating at least a type or a size of the one or more annotations to be generated for the object in the second image.

[0172] 4. The computer-implemented method of clause 1, wherein removing comprises:

[0173] recognizing at least a portion of the first image as the text using an optical character recognition (OCR) model; and

[0174] The text is removed from the first image by setting pixel values ​​at one or more pixel locations corresponding to the recognized text to pixel values ​​determined based in part on pixel values ​​of the object proximate to the one or more pixel locations.

[0175] 5. A computer-implemented method according to clause 1, wherein blending the text into the second image of the object allows the one or more annotations to be generated for the object in the second image without the generative diffusion model modifying the semantic meaning of the text.

[0176] 6. The computer-implemented method of clause 1, wherein the blending is performed using text blending weights and annotation blending weights.

[0177] 7. A computer-implemented method according to clause 6, wherein the mixing includes: calculating a weighted average of pixel values ​​at one or more pixel positions corresponding to the text, the calculation being performed based on at least one of the text mixing weights or the annotation mixing weights.

[0178] 8. A processor, comprising:

[0179] One or more circuits for:

[0180] removing text from the texture represented in the first image;

[0181] providing the first image of the texture as input to a generative diffusion model after removing the text;

[0182] receiving as an output of said generating a diffusion model a second image comprising one or more annotations applied to said texture; and

[0183] The text is blended back into the texture with the one or more annotations in the second image.

[0184] 9. The processor of clause 8, wherein the one or more annotations include at least one type of defect to be applied to the representation of the object in the second image.

[0185] 10. The processor of clause 8, wherein the one or more circuits are further configured to:

[0186] A textual cue is provided as an additional input to the generative diffusion model, the textual cue indicating at least a type or a size of the one or more annotations to be generated for the object in the second image.

[0187] 11. The processor of clause 8, wherein the one or more circuits are further configured to:

[0188] Recognize the text using an optical character recognition (OCR) model; and

[0189] The text is removed from the first image by setting pixel values ​​at one or more pixel locations corresponding to the recognized text to pixel values ​​determined based in part on pixel values ​​of the object proximate to the one or more pixel locations.

[0190] 12. A processor according to clause 8, wherein blending the text into the second image of the object allows the one or more annotations to be generated for the object in the second image without the generative diffusion model modifying the semantic meaning of the text.

[0191] 13. A processor according to clause 8, wherein the blending is performed using text blending weights and annotation blending weights.

[0192] 14. A processor according to clause 8, wherein the mixing includes: calculating a weighted average of pixel values ​​of one or more pixel positions corresponding to the text, the calculation being performed based on at least one of the text mixing weights or the annotation mixing weights.

[0193] 15. The processor of clause 8, wherein the processor is comprised of at least one of:

[0194] A system for performing simulation operations;

[0195] Systems for performing simulated operations to test or validate autonomous machine applications;

[0196] Systems for performing digital twin operations;

[0197] A system for performing light transport simulations;

[0198] Systems for rendering graphical output;

[0199] Systems for performing deep learning operations;

[0200] Systems implemented using edge devices;

[0201] Systems for generating or presenting virtual reality (VR) content;

[0202] Systems for generating or presenting augmented reality (AR) content;

[0203] Systems for generating or presenting mixed reality (MR) content;

[0204] A system comprising one or more virtual machines VM;

[0205] A system implemented at least in part in a data center;

[0206] A system for performing hardware testing using simulation;

[0207] A system for performing generative content operations using a language model;

[0208] Systems for synthetic data generation;

[0209] A system for performing generative AI operations using a large language model (LLM);

[0210] A collaborative content creation platform for 3D assets; or

[0211] A system implemented at least in part using cloud computing resources.

[0212] 16. A system comprising:

[0213] One or more processors for adding one or more enhancements to a texture comprising semantic content in a synthesized input image, the one or more processors for generating an output image representing the one or more enhancements applied to the texture using a generative diffusion model having a version of the synthesized input image with the semantic content removed, the one or more processors further for blending the removed semantic content back into the texture in the output image.

[0214] 17. The system of clause 16, wherein the one or more enhancements comprise at least one type of defect to be applied to the representation of the object in the output image.

[0215] 18. A system according to clause 16, wherein the one or more processors are further configured to provide a hint as an additional input to the generative diffusion model, the hint indicating at least a type or strength of the one or more annotations to be generated for the object in the output image.

[0216] 19. The system of clause 16, wherein the one or more processors are further configured to:

[0217] Recognize the semantic content using an optical character recognition (OCR) model; and

[0218] The semantic content is removed 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 proximate to the pixel locations.

[0219] 20. The system of clause 16, wherein the system comprises at least one of:

[0220] A system for performing simulation operations;

[0221] Systems for performing simulated operations to test or validate autonomous machine applications;

[0222] Systems for performing digital twin operations;

[0223] A system for performing light transport simulations;

[0224] Systems for rendering graphical output;

[0225] Systems for performing deep learning operations;

[0226] A system for performing generative AI operations using a large language model (LLM);

[0227] Systems implemented using edge devices;

[0228] Systems for generating or presenting virtual reality (VR) content;

[0229] Systems for generating or presenting augmented reality (AR) content;

[0230] Systems for generating or presenting mixed reality (MR) content;

[0231] A system comprising one or more virtual machines VM;

[0232] A system implemented at least in part in a data center;

[0233] A system for performing hardware testing using simulation;

[0234] A system for performing generative content operations using a language model;

[0235] Systems for synthetic data generation;

[0236] A collaborative content creation platform for 3D assets; or

[0237] A system implemented at least in part using cloud computing resources.

[0238] Other variations are within the spirit of the present disclosure. Thus, while the disclosed technology is susceptible to various modifications and alternative constructions, certain illustrated embodiments thereof are shown in the drawings and have been described in detail above. However, it should be understood that there is no intention to limit the disclosure to one or more specific forms disclosed, but on the contrary, it is intended to cover all modifications, alternative constructions, and equivalents that fall within the spirit and scope of the present disclosure as defined by the appended claims.

[0239] Unless otherwise noted or clearly contradictory to the context, in the context of describing the disclosed embodiments (particularly in the context of the appended claims), the use of the terms "one" and "an" and "the" and similar references should be interpreted as covering the singular and plural, rather than as definitions of terms. Unless otherwise noted, the terms "include", "have", "include" and "contain" should be interpreted as open terms (meaning "including but not limited to") unless otherwise noted. The term "connected" (which refers to a physical connection when unmodified) should be interpreted as partially or completely included, attached to or connected together, even if there are some interventions. Unless otherwise noted herein, references to numerical ranges herein are intended only to be used as a shorthand method of referring to each individual value falling within the range, respectively, and each individual value is incorporated into the specification as if it were individually described herein. Unless otherwise noted or contradictory to the context, the use of the term "set" (e.g., "item set") or "subset" should be interpreted as a non-empty set including one or more members. Furthermore, unless otherwise indicated or contradicted by context, the term "subset" of a corresponding set does not necessarily mean a proper subset of the corresponding set, but rather a subset and a corresponding set may be equivalent.

[0240] Unless expressly indicated otherwise or clearly contradicted by context, conjunctions such as phrases of the form "at least one of A, B, and C" or "at least one of A, B and C" are understood in context to be generally used to refer to an item, clause, or the like that may be A or B or C, or any non-empty subset of the set A and B and C. For example, in the illustrative example of a set having three members, the conjunction phrases "at least one of A, B, and C" and "at least one of A, B and C" refer to any of the following sets: {A}, {B}, {C}, {A, B}, {A, C}, {B, C}, {A, B, C}. Thus, such conjunction language is not generally intended to imply that certain embodiments require the presence of at least one of A, at least one of B, and at least one of C. In addition, unless expressly indicated otherwise or contradicted by context, the term "plurality" refers to a plural state (e.g., "plurality of items" means a plurality of items). The number of items in a plurality of items is at least two, but may be more if expressly indicated or indicated by context. Further, the phrase "based on" means "based at least in part on" rather than "based solely on" unless otherwise specified or clear from context.

[0241] Unless otherwise indicated herein or clearly contradictory to the context, the operations of the processes described herein may be performed in any suitable order. In at least one embodiment, processes such as those described herein (or variations and / or combinations thereof) are performed under the control of one or more computer systems configured with executable instructions and are implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that are jointly executed on one or more processors by hardware or a combination thereof. In at least one embodiment, the code is stored on a computer-readable storage medium in the form of, for example, a computer program that includes a plurality of instructions that can be executed by one or more processors. In at least one embodiment, the computer-readable storage medium is a non-transitory computer-readable storage medium that excludes transient signals (e.g., propagated transient electrical or electromagnetic transmissions), but includes non-transitory data storage circuits (e.g., buffers, caches, and queues). 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 (or other memory for storing executable instructions) on which executable instructions are stored, which, when executed by one or more processors of a computer system (i.e., as a result of being executed), causes the computer system to perform the operations described herein. In at least one embodiment, a set of non-transitory computer-readable storage media includes a plurality of non-transitory computer-readable storage media, and one or more of the individual non-transitory storage media in the plurality of non-transitory computer-readable storage media lacks all the code, but the plurality of non-transitory computer-readable storage media stores all the code together. In at least one embodiment, the executable instructions are executed so 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 instructions, while a graphics processing unit ("GPU") executes other instructions. In at least one embodiment, different components of the computer system have separate processors, and different processors execute different subsets of instructions.

[0242] Thus, in at least one embodiment, a computer system is configured to implement one or more services that individually or collectively perform the operations of the processes described herein, and such a computer system is configured with applicable hardware and / or software that enables the implementation of the operations. In addition, a computer system that implements at least one embodiment of the present disclosure is a single device, and in another embodiment is a distributed computer system that includes multiple devices that operate in different ways, so that the distributed computer system performs the operations described herein, and so that a single device does not perform all operations.

[0243] The use of any and all examples or exemplary language (e.g., "such as") provided herein is intended only to better illustrate embodiments of the present disclosure and does not limit the scope of the disclosure unless otherwise required. No language in the specification should be construed as indicating that any non-claimed element is essential to practicing the disclosure.

[0244] All references, including publications, patent applications, and patents, cited herein are hereby incorporated by reference to the same extent as if each reference were individually and specifically indicated to be incorporated by reference and were set forth in its entirety herein.

[0245] In the specification and claims, the terms "coupled" and "connected," as well as their derivatives, may be used. It should be understood that these terms may not be intended as synonyms for each other. On the contrary, in specific 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" may also mean that two or more elements are not in direct contact with each other, but still cooperate or interact with each other.

[0246] Unless explicitly stated otherwise, it is to be understood that throughout the specification, terms such as “processing”, “computing”, “calculating”, “determining” and the like refer to the actions and / or processes of a computer or computing system or similar electronic computing device that processes and / or converts data represented as physical quantities (e.g., electronic) in registers and / or memories of the computing system into other data similarly represented as physical quantities in the memories, registers or other such information storage, transmission or display devices of the computing system.

[0247] In a similar manner, the term "processor" may refer to any device or part of a memory that processes electronic data from registers and / or memory and converts the electronic data into other electronic data that can be stored in registers and / or memory. As a non-limiting example, a "processor" may be a CPU or a GPU. A "computing platform" may include one or more processors. As used herein, a "software" process may include, for example, software and / or hardware entities that perform work over time, such as tasks, threads, and intelligent agents. Similarly, each process may refer to multiple processes to execute instructions sequentially or in parallel, continuously or intermittently. The terms "system" and "method" may be used interchangeably herein, as long as a system may embody one or more methods, and a method may be considered a system.

[0248] In this document, reference may be made to obtaining, acquiring, receiving or inputting analog or digital data into a subsystem, a computer system or a computer-implemented machine. It is possible to obtain, acquire, receive or input analog and digital data in a variety of ways, such as by receiving data as a parameter of a function call or a call to an application programming interface. In some implementations, the process of obtaining, acquiring, receiving or inputting analog or digital data can be accomplished by transmitting data via a serial or parallel interface. In another implementation, the process of obtaining, acquiring, receiving or inputting analog or digital data can be accomplished by transmitting data from a providing entity to an acquiring entity via a computer network. It is also possible to reference to providing, outputting, transmitting, sending or presenting analog or digital data. In various examples, the process of providing, outputting, transmitting, sending or presenting analog or digital data can be accomplished by transmitting data as an input or output parameter of a function call, an application programming interface or an interprocess communication mechanism.

[0249] Although the above discussion sets forth example implementations of the described techniques, other architectures may be used to implement the described functionality and are intended to fall within the scope of the present disclosure. In addition, although specific responsibilities are defined above for discussion purposes, various functions and responsibilities may be allocated and divided in different ways, depending on the circumstances.

[0250] Furthermore, although the subject matter has been described in language specific to structural features and / or methodological acts, it should 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.

Claims

1. A computer-implemented method comprising: removing text from the object represented in the first image; providing the first image of the object without the removed text as input to a generative diffusion model; receiving a second image of the object as an output of said generating a diffusion model, the second image comprising one or more annotations of the object; as well as The text is blended into the second image of the object such that the one or more annotations are represented as being 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 the representation of the object in the second image.

3. The computer-implemented method of claim 1 , further comprising: A textual cue is provided as an additional input to the generative diffusion model, the textual cue indicating at least a type or a size of the one or more annotations to be generated for the object in the second image.

4. The computer-implemented method of claim 1 , wherein removing comprises: recognizing at least a portion of the first image as the text using an optical character recognition (OCR) model; as well as The text is removed from the first image by setting pixel values ​​at one or more pixel locations corresponding to the recognized text to pixel values ​​determined based in part on pixel values ​​of the object proximate to the one or more pixel locations.

5. The computer-implemented method of claim 1, wherein blending the text into the second image of the object allows the one or more annotations to be generated for the object in the second image without the generative diffusion model modifying the semantic meaning of the text.

6. The computer-implemented method of claim 1, wherein the blending is performed using a text blending weight and an annotation blending weight.

7. The computer-implemented method of claim 6, wherein the mixing comprises: A weighted average of pixel values ​​of one or more pixel positions corresponding to the text is calculated, the calculation being performed according to at least one of the text mixing weight or the annotation mixing weight.

8. A processor, comprising: One or more circuits for: removing text from the texture represented in the first image; providing the first image of the texture as input to a generative diffusion model after removing the text; receiving as an output of said generating a diffusion model a second image, said second image comprising one or more annotations applied to said texture; as well as The text is blended back into the texture with the 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 the representation of the object in the second image.

10. The processor of claim 8, wherein the one or more circuits are further configured to: A textual cue is provided as an additional input to the generative diffusion model, the textual cue indicating at least a type or a size of the one or more annotations to be generated for the object in the second image.

11. The processor of claim 8, wherein the one or more circuits are further configured to: Recognize the text using an optical character recognition (OCR) model; and The text is removed from the first image by setting pixel values ​​at one or more pixel locations corresponding to the recognized text to pixel values ​​determined based in part on pixel values ​​of the object proximate to the one or more pixel locations.

12. The processor of claim 8, wherein blending the text into the second image of the object allows the one or more annotations to be generated for the object in the second image without the generative diffusion model modifying a semantic meaning of the text.

13. The processor of claim 8, wherein the blending is performed using a text blending weight and an annotation blending weight.

14. The processor of claim 8, wherein the mixing comprises: A weighted average of pixel values ​​of one or more pixel positions corresponding to the text is calculated, the calculation being performed according to at least one of the text mixing weight or the annotation mixing weight.

15. The processor of claim 8, wherein the processor is included in at least one of: A system for performing simulation operations; Systems for performing simulated operations to test or validate autonomous machine applications; Systems for performing digital twin operations; A system for performing light transport simulations; Systems for rendering graphical output; Systems for performing deep learning operations; Systems implemented using edge devices; Systems for generating or presenting virtual reality (VR) content; Systems for generating or presenting augmented reality (AR) content; Systems for generating or presenting mixed reality (MR) content; A system comprising one or more virtual machines VM; A system implemented at least in part in a data center; A system for performing hardware testing using simulation; A system for performing generative content manipulation using a language model; Systems 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 enhancements to a texture comprising semantic content in a synthesized input image, the one or more processors for generating an output image representing the one or more enhancements applied to the texture using a generative diffusion model having a version of the synthesized input image with the semantic content removed, the one or more processors further for blending the removed semantic content back into the texture in the output image.

17. The system of claim 16, wherein the one or more enhancements include at least one type of defect to be applied to the representation of the object in the output image.

18. The system of claim 16, wherein the one or more processors are further configured to provide a hint as an additional input to the generative diffusion model, the hint indicating at least a type or strength of the one or more annotations to be generated for the object in the output image.

19. The system of claim 16, wherein the one or more processors are further configured to: Recognize the semantic content using an optical character recognition (OCR) model; and The semantic content is removed 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 proximate to the pixel locations.

20. The system of claim 16, wherein the system comprises at least one of: A system for performing simulation operations; Systems for performing simulated operations to test or validate autonomous machine applications; Systems for performing digital twin operations; A system for performing light transport simulations; Systems for rendering graphical output; Systems for performing deep learning operations; A system for performing generative AI operations using a large language model (LLM); Systems implemented using edge devices; Systems for generating or presenting virtual reality (VR) content; Systems for generating or presenting augmented reality (AR) content; Systems for generating or presenting mixed reality (MR) content; A system comprising one or more virtual machines VM; A system implemented at least in part in a data center; A system for performing hardware testing using simulation; A system for performing generative content manipulation using a language model; Systems 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