16 results about "Image colorization" patented technology

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.

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.

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.

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.

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.

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.

This application provides an image colorization processing method and related apparatus. The method includes: retrieving an image to be processed from a central processing unit (CPU) via an open graphics library; performing graphical processing on the image to obtain a graphical processing result; retrieving parameter data of a deep learning model from the CPU via the open graphics library; configuring the deep learning model using the parameter data; and retrieving the graphical processing result from the open graphics library and applying it to the configured deep learning model for colorization rendering, thereby sending the colorization rendering result to a display device for display. This eliminates the need to send the colorization rendering result back to the CPU, allowing it to be directly sent to the display device for display, reducing data transmission time and resource consumption during data transmission, and improving the efficiency of colorization rendering.

The invention relates to the technical field of short-wave infrared imaging, and provides a physical data dual-drive short-wave infrared image colorization wave band optimization method and device. Aiming at the problem of exponential explosion of hyperspectral / multispectral waveband combinations, the method abandons an exhaustion training method with expensive calculation, utilizes a layered screening framework, firstly utilizes a physical model to determine candidate wavebands, and then utilizes improved statistical indexes to quickly perform unsupervised dimensionality reduction to obtain a small amount of high-potential combinations. And finally, carrying out generative verification on the high-potential combination to obtain an optimal wave band combination. The strategy not only ensures the physical interpretability of wave band selection, but also greatly reduces the time cost and the computing power consumption for searching the optimal solution.

The application discloses a kind of cartoon image coloring method, system, device and storage medium, wherein method includes: obtaining the size size H×W cartoon image, cartoon image is down-sampled, obtains first resolution image;First resolution image is input based on self-attention mechanism Transformer network, carries out feature extraction, and the color distribution of each pixel in first resolution image is predicted, obtains rough coloring image with color depth;Rough coloring image and cartoon image are input based on the promotion network of adversarial generation, and the resolution and color depth are reconstructed, obtain second resolution image;Second resolution image is up-sampled, and the size size H×W fine coloring image is obtained.The application utilizes Transformer model to carry out the rough coloring of low resolution low color depth, and then reconstructs resolution and color depth using adversarial generation model, which can effectively improve the coloring effect of cartoon image, and can be widely applied in the field of image processing technology.

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.