47 results about "Image colorization" patented technology

A system and method are provided for generating colorized image data for a single-channel image using a ML network, as well as a system and method for training the ML network. The image colorization method includes: obtaining single-channel image data representing a single-channel image; generating image feature data as a result of inputting the single-channel image data into an encoder; generating a pixel decoder output through inputting the image feature data into a pixel decoder; generating a color decoder output through inputting the image feature data into a color decoder; and generating colorized image data based on the color decoder output and the pixel decoder output, wherein the colorized image data represents a colorized version of the single-channel image.

The invention provides a multi-condition guide text image generation method based on decoupling and a multi-domain guide strategy. According to the method, an image meeting text description and spatial alignment at the same time can be generated according to the text and any spatial condition. Specifically, structure representation and appearance representation in the image generation process are decoupled, and two independent guide branches, namely an appearance guide branch and a structure guide branch, are designed. The two branches guide the generation process to be highly aligned with the input structure of the guide branch while guiding the appearance content in the accurate expression text through a classifier guide strategy. Besides, in order to realize better structural consistency, the method provides a multi-domain guide strategy, and more comprehensive structural supervision is realized by combining a spatial domain and a frequency domain. According to the method, the text generation image guided by any space condition can be realized, the method can be used in various generative models in a plug-and-play manner, and common downstream tasks such as image deblurring, image coloring, image restoration and image editing can be completed.

The invention discloses a synthetic aperture radar (SAR) image colorization system, which comprises a data acquisition module, a model training module and a colorized image generation module, the data acquisition module is used for acquiring a multi-modal data set; the model training module is used for training a noise prediction model by using the multi-modal data set, and the noise prediction module is obtained by constructing a cross attention mechanism network; and the colorized image generation module is used for inputting a to-be-predicted image into the noise prediction model to obtain a color optical image. The method is suitable for disaster monitoring, landform investigation and other scenes needing high-precision SAR image analysis.

The application discloses a synthetic aperture radar (SAR) image colorization system, comprising a data acquisition module, a model training module and a colorized image generation module; the data acquisition module is used for acquiring a multi-modal data set; the model training module is used for training a noise prediction model by using the multi-modal data set, wherein the noise prediction model is obtained by constructing a cross-attention mechanism network; and the colorized image generation module is used for inputting a to-be-predicted image into the noise prediction model to obtain a color optical image. The application is suitable for disaster monitoring, landform surveying and other scenes requiring high-precision SAR image analysis.

The present invention discloses a near-infrared image colorization method based on a two-stage conditional generative adversarial network. The near-infrared image colorization method based on the two-stage conditional generative adversarial network comprises the following steps: S1: obtaining a near-infrared grayscale image; S2: constructing a grayscale preprocessing module for the near-infrared image; S3: using the grayscale preprocessing module for the near-infrared image to preprocess the near-infrared grayscale image to obtain a grayscale image; S4: constructing an image colorization module; S5: using the image colorization module to colorize the grayscale image to obtain a colored generated image, wherein the image colorization module is further used to discriminate color feature vectors extracted from the colored generated image and a training image, and obtain a discrimination result for training the image colorization module. The present invention can solve the problem that existing image colorization methods lack corresponding grayscale processing for near-infrared images containing a large amount of noise information, resulting in the colored image having an overall visual effect of bright and dark flickering.

A computer-implemented method for selectively replacing a color of an object in an original image due to color blindness of a viewer. The method includes identifying whether there are color groups that are hard to be distinguished at a border between one or more objects in an original image. The method further includes generating a grayscale image from the original image and estimating an original color of each pixel in the original image by inputting the generated grayscale image to an automatic colorization artificial intelligence (AI) model. The method further includes determining at least one color group for which color replacement is to be performed and replacing the determined at least one color group with a color that is easily perceived by the person having a color vision deficiency and that is easily distinguished from the other color groups at the border between the identified one or more objects.

The embodiment of the invention provides a coloring method, electronic equipment and an electronic chip. The method comprises the steps that a first coloring rate texture map for a first image is acquired, the first image is an image generated by variable-resolution coloring rendering according to current image frame data, and the resolution of the first image is lower than the rendering target resolution of an image frame; and performing artificial intelligence super-division on the first image based on the first coloring rate texture map, improving the resolution of the first image, and generating a second image meeting the rendering target resolution. According to the coloring method provided by the embodiment of the invention, image coloring rendering is performed in combination with variable-resolution coloring and artificial intelligence super-resolution, and the fuzzy region in the variable-resolution coloring result is repaired by adopting the artificial intelligence super-resolution, so that the image rendering quality is improved, and the image rendering overhead is reduced.

Computing systems and methods for neural network-based image colorization are provided. A computing system obtains a reference color image by selective application of a color effect on a region of interest of an input image and controls a display device to display a first node graph on a graphical user interface of an image / video editing application. The first node graph includes a colorization node representing a first workflow for colorizing at least a first object in a grayscale image of a first image feed. The computing system selects the reference color image based on user input and executes the first workflow associated with the colorization node by feeding the reference color image and the first image feed as inputs to a neural network-based colorization model. The computing system receives a second image feed including a colorized image as an output of the neural network-based colorization model for the inputs.

The application discloses an image coloring method and device based on iterative optimization and a medium, relates to the technical field of image processing, and comprises the following steps: acquiring a grayscale image; performing initial coloring on the grayscale image by using a trained conditional coloring model to obtain an initial coloring result; performing color evaluation on the initial coloring result by using a trained evaluation model, identifying a region in the initial coloring result that does not meet a set standard of color confidence, and obtaining an unsatisfactory region; performing re-coloring on the unsatisfactory region by using the trained conditional coloring model to obtain an updated coloring result; replacing the initial coloring result with the updated coloring result, repeating the re-coloring and evaluation processes, obtaining a final coloring result, and decoding the final coloring result to obtain a final color image. The application realizes higher reality and fidelity in image coloring.

This invention discloses a high-resolution grayscale image layered colorization method based on zero-domain decomposition. This method employs a layered image processing strategy. First, the input high-resolution grayscale image is downsampled, and the downsampled result is colorized using a text image model to obtain a low-resolution color result. Then, detail information from the high-resolution grayscale image and color information from the low-resolution color result are extracted based on zero-domain decomposition. Finally, the extracted color information is corrected using prior knowledge from a diffusion model, while the extracted detail information is injected to obtain the high-resolution color result. This invention, based on zero-domain decomposition, proposes color image information decomposition and diffusion model-based color information correction in the grayscale image layered colorization process, which can be used to generate color results highly consistent with the detail information in the high-resolution grayscale image. The color image information decomposition proposed in this invention is easily integrated with existing layered grayscale image colorization methods.

The invention discloses an image processing method and device, a storage medium and electronic equipment. The method comprises the steps of obtaining an original image, a text instruction and a target color corresponding to the text instruction; inputting the original image, the target color and the text instruction into an image editing pre-training model to obtain a target image corresponding to the original image; the target image is an image obtained by adjusting the color of a target area in the original image to the target color; wherein the image editing pre-training model is an image coloring model obtained by training based on a preset loss function through a diffusion model constructed by an image encoder, a text encoder, an iterative de-noising device and an image decoder. According to the invention, the image accurately matched with the color intention specified by the user can be generated.

An image processing network for image colorization, image color enhancement, image super resolution, or any similar image-to-image processing is converted into an automatic video processing network with temporal stability by addition of a temporal referencing network (TRN). The implementation of the image processing network may remain unmodified, with the temporal information added based on the TRN. The TRN is configured to add temporal information to an input and to an output to an image processing network. The temporal information added to the input and the output includes multiple temporal reference maps generated for one or more input images and one or more output images of the image processing network. Temporal relations are determined based on application of the multiple temporal reference maps for the one or more input images to a recurrent network of the TRN.

A system and method are provided for generating colorized image data for a single-channel image using a ML network, as well as a system and method for training the ML network. The image colorization method includes: obtaining single-channel image data representing a single-channel image; generating image feature data as a result of inputting the single-channel image data into an encoder; generating a pixel decoder output through inputting the image feature data into a pixel decoder; generating a color decoder output through inputting the image feature data into a color decoder; and generating colorized image data based on the color decoder output and the pixel decoder output, wherein the colorized image data represents a colorized version of the single-channel image.

The invention discloses an image coloring method and device based on iterative optimization and a medium, and relates to the technical field of image processing, and the method comprises the steps: obtaining a grayscale image; performing initial coloring on the grayscale image by using the trained condition coloring model to obtain an initial coloring result; performing color evaluation on the initial coloring result by using a trained evaluation model, and identifying an area which does not accord with a set standard of color confidence in the initial coloring result to obtain an unsatisfied area; re-coloring the unsatisfied area by using the trained condition coloring model to obtain an updated coloring result; and replacing the initial coloring result with the updated coloring result, repeating the re-coloring and evaluation process to obtain a final coloring result, and decoding the final coloring result to obtain a final color image, thereby realizing higher sense of reality and fidelity in the aspect of image coloring.

The invention discloses an automatic image coloring method based on semantic segmentation and a generative adversarial network, and relates to the technical field of computer vision and deep learning. According to the technical scheme, a model with ChromaGAN as a basic framework is adopted; designing a semantic segmentation network used for helping the model to obtain more semantic analysis information; adding a shape prior module into the segmentation network; an external storage network is used for guiding the coloring main network, color histogram information and category information of the image are extracted, and the information is stored in the storage network; and fusing the stored color histogram information and semantic information to improve the color saturation and finish coloring. The method has the beneficial effects that through an innovative technical scheme, key problems in an existing image coloring technology are solved, the coloring quality, the color saturation and the sense of reality are remarkably improved, meanwhile, the generalization ability and the training stability of the model are enhanced, the user interaction cost is reduced, and the user experience is improved. And a new thought and a new solution are provided for development and application of an image coloring technology.

This application provides an image colorization processing method and related apparatus. The method includes: acquiring an image to be processed, the image including a first region and a second region, the first region being located at the edge of the second region, and the brightness of the first region being greater than that of the second region; determining the range of the first region corresponding to the first region in the image to be processed; determining the boundary of the first region based on the range of the first region; locating the corners of the image to be processed based on the boundary of the first region, and determining the region of interest (ROI) corresponding to the image to be processed using the location result. The range of the first region determined in this way is accurate, therefore even if the image to be processed is offset or has ripples, the ROI can be accurately determined based on the range of the first region. Furthermore, the entire ROI determination process is completed through program control without the need for additional hardware, thus reducing costs.

The invention discloses a multi-information progressive fusion image colorization method based on a deep convolutional neural network. The method is composed of five core modules: an input module is responsible for receiving an original image and carrying out preprocessing operations such as graying and normalization; the feature extraction module is actually a VGG network and is responsible for extracting multi-level features of the image; the multi-information fusion module adopts a channel attention mechanism to collaboratively fuse gray features, edge features extracted by a Canny edge detector and semantic features extracted by a DeepLabv3 + semantic segmentation network; the progressive colorization generation and optimization module comprises a plurality of U-Net sub-networks, and realizes colorization image generation from coarse to fine through a staged generation strategy in combination with joint optimization of L1 loss, perception loss and adversarial loss; and the output module carries out reverse normalization processing on the result. According to the method, the problems of color distortion and detail loss in the prior art are effectively solved, the color image with accurate color, rich details and vivid vision can still be generated in a complex scene, and the method can be widely applied to the fields of old film color restoration, medical image enhancement and the like.

Embodiments of the present application provide an image processing method and device, electronic equipment and storage medium, and relate to the technical field of image processing. The method comprises: obtaining a target object's to-be-processed image (for example, a grayscale digital image); performing image feature extraction on the to-be-processed image to obtain a first feature map; determining coloring reference information of the to-be-processed image based on a color system to which the to-be-processed image belongs, and fusing the coloring reference information to the first feature map to obtain a second feature map having coloring reference information; coloring the second feature map based on a reference palette obtained by training a first training set to obtain an image coloring result of the to-be-processed image, the first training set comprising at least one color image of the target object, and the reference palette being a set of colors contained in the color image of the target object in the first training set. The embodiments of the present application can effectively improve the coloring accuracy of grayscale digital images, and further improve the coloring effect of the to-be-processed image.

The application relates to an image coloring method based on multi-modal content coding, which comprises the following steps: acquiring multi-modal data, including an image, text, a category and a color palette, wherein the text is a descriptive sentence of the image, the category is a style attribute of the image, and the color palette comprises multiple colors to be generated; respectively coding the multi-modal data and fusing the multi-modal data to obtain color palette generation fusion coding; generating the colors in the color palette based on the color palette generation fusion coding by using a color palette generation network; re-coding the multi-modal data based on the generated color palette and fusing the multi-modal data to obtain coloring fusion coding; and coloring the image based on the coloring fusion coding by using an image coloring network. Compared with the prior art, the intelligent color design process fully considers the influence of culture, and realizes automatic coloring of the image with a specific cultural style.

The application discloses a low-illumination grayscale image colorization method, comprising the following steps: acquiring a to-be-processed image; identifying the scene type of the to-be-processed image by using a trained special scene recognition model; and performing colorization on the to-be-processed image by selecting a trained micro-light image colorization model suitable for the special scene according to the scene type. The low-illumination grayscale image colorization method significantly improves the grayscale image colorization effect of the special scene under low-illumination conditions, especially in the case of high-quality data set, the quality of the generated image is obviously improved; the CycleGAN is optimized, the color restoration effect is improved, the network structure is simplified, the calculation speed is improved, and an efficient and fast image colorization algorithm is provided for the special scene.

This application relates to the field of shortwave infrared imaging technology, and provides a method and apparatus for optimizing color bands in shortwave infrared images driven by both physical data and technical data. Addressing the problem of exponentially increasing combinations of hyperspectral / multispectral bands, this method abandons the computationally expensive exhaustive training method and utilizes a hierarchical screening framework. First, a physical model is used to determine candidate bands. Then, improved statistical indices are used to quickly perform unsupervised dimensionality reduction to obtain a small number of high-potential combinations. Finally, generative validation of these high-potential combinations yields the optimal band combination. This strategy ensures the physical interpretability of band selection while significantly reducing the time cost and computational consumption in finding the optimal solution.

This invention relates to a high-resolution, high-fidelity panchromatic image colorization method based on DSM constraints from the Gaofen-7 satellite. It involves acquiring forward and backward panchromatic and backward multispectral images from the Gaofen-7 satellite, preprocessing them to obtain registered panchromatic, DSM, and true-color images, and constructing a DSM-constrained dual-decoder panchromatic image colorization network. Multi-scale features of the DSM and panchromatic images are extracted using a dual-branch ConvNeXt encoder. An adaptive feature selection fusion module fuses and upsamples the multi-scale features of the DSM and panchromatic images, inputting them into a symmetrical luminance decoder and color decoder to reconstruct the luminance and color channels in CIELAB space. The network's internal parameters are optimized by incorporating perceptual and color losses to alleviate problems of low color fidelity, low saturation, and color distortion, ultimately reconstructing a high-resolution, high-fidelity true-color image.

The invention discloses an adaptive contrast learning infrared image colorization method and system based on human visual features, and belongs to the technical field of image colorization. A self-adaptive contrast learning infrared image colorization method based on human visual features comprises the following steps: step 1, preparing an infrared data set: preprocessing a training set I and a training set II, and preprocessing a training set image with a fixed size; the first training set is a KAI ST data set, the second training set is an FL IR data set, and a fixed-size training set image is output by taking an original data set image as input; 2, constructing a network model, wherein the whole network is composed of an adversarial network, and the adversarial network comprises a generator, a discriminator, a sample marking operation and a generation fitting operation; contrast learning is introduced, brand new positive and negative samples are constructed, and a generator is designed, so that an output infrared image colorization result is more real and accords with local and overall feelings of visual observation of human eyes.

The present disclosure provides an interactive video coloring method, system, device and medium. The interactive video coloring method adjusts the feature map of the image coloring network before reconstructing the color channel to achieve the purpose of improving the video coloring quality. During the coloring process, no changes are made to the structure of the image coloring network, and only corresponding adjustments are made to one layer of the feature map. A memory unit and a correction unit are used to record the semantic and color information of the historical coloring frames respectively, and the intermediate structure of the current frame is modified using the coloring result of the latest frame, thereby significantly improving the visual quality of the output video.

The invention provides a grayscale image colorization method and device, electronic equipment and a storage medium, and belongs to the technical field of digital image processing, and the method comprises the steps: determining mark pixels based on a mark image and an original image; for each pixel point, a plurality of local windows are generated, an optimal local window is determined based on the plurality of local windows, and the plurality of local windows are local windows in different directions; for each pixel point, the weight of the pixel point is determined based on the brightness of a neighbor pixel and the brightness of the pixel point, the neighbor pixel is a neighborhood pixel in the optimal local window of the pixel point, and the weight reflects the influence degree of the neighbor pixel of the pixel point on the pixel point; generating a sparse matrix based on the weight of each pixel point; and based on the mark pixels and the sparse matrix, determining the value of each pixel point to obtain a color image. According to the method, edge blurring and color leakage can be avoided, the manual labeling workload is reduced, and the calculation complexity is low.

Implementations described herein relate to methods, systems, and computer-readable media to train and use a machine-learning model to colorize a grayscale image that depicts a person. In some implementations, a computer-implemented method includes receiving the grayscale image. The method further includes generating a colorized image based on the grayscale image as output of a trained convolutional neural network (CNN) by providing the grayscale image as input to the trained CNN. In some implementations, the trained CNN performs part segmentation to detect one or more parts of the person and colorizes the grayscale image.

The present invention discloses an image coloring method based on Transformer and generative adversarial network, which uses the generative adversarial network GAN and Transformer instead of simply using the convolutional neural network CNN to solve the image coloring problem. The proposed Transformer-GAN reduces excessive computing resources through a window-based multi-head self-attention mechanism and a discriminator friendly to computing resources. The local enhancement forward propagation network and skip connections ensure that shallow features can be effectively transmitted and utilized in the network, enabling Transformer-GAN to effectively capture the correlation between global and local information. The best training process is also explored through data augmentation and objective function selection. The formed color image generator and discriminator enable Transformer-GAN to perform well in image colorization, achieving the best visual effect.

Embodiments of the present application provide a shading method, an electronic device, and an electronic chip. The method comprises: acquiring a first shading rate texture map for a first image, the first image being an image generated by performing variable-rate shading rendering on the basis of current image frame data, and a resolution of the first image being lower than a target rendering resolution of an image frame; on the basis of the first shading rate texture map, performing artificial intelligence super-resolution on the first image, increasing the resolution of the first image, and generating a second image meeting the target rendering resolution. According to the shading method provided by the embodiments of the present application, image shading rendering is performed in combination with variable-rate shading and artificial intelligence super-resolution, and a fuzzy area in a variable-rate shading result is repaired by using artificial intelligence super-resolution, improving image rendering quality, and reducing image rendering overhead.

The invention discloses a pneumonia image identification and classification method based on an improved Swin Transform model. The method comprises the following steps: S100, carrying out preprocessing of three aspects of content standardization, image colorization and format unification on original data; s200, performing data enhancement on the input training set image; s300, selecting ResNet-34 as a teacher model, and carrying out pre-training on the processed training set by using the teacher model to obtain a hard tag for guiding a student model; s400, carrying out training by using an improved Swin Transform student model, and improving the training efficiency of the student model by using a method including but not limited to MSG Token and shuffle; when the loss function is calculated, a hard tag output by the teacher model is used for guiding the student model; and S500, importing a chest radiograph image to be classified, and obtaining a classification result by using the trained student model. According to the method, the problems of insufficient generalization ability, high calculation complexity, insufficient image local feature extraction and the like when an existing deep learning model is used for processing large-scale data can be solved.

Existing sketch generation techniques have disadvantages such as less accuracy over complex sketches, incapable of scaling for complex sketches involving shading and textures, and high computational demands of deep reinforcement learning and lack an inherent sequence order while generating strokes. Embodiments disclosed herein provide a method and system which converts an input image to a sketch, and further obtains an associated sequence of strokes. Further, a sketch sequencing to orchestrate the sequence of strokes is performed, during which a stroke sequence is generated for a constructed sketch of strokes. Based on the generated stroke sequence, the input image is recreated. Further, a paint sequence for the recreated image is generated, wherein by executing the paint sequence, the recreated image is painted to match color of the input image.