Abstract: Embodiments of the disclosure provide a method and a device for generating a sticker. The method includes: obtaining material images of a plurality of components on an avatar; determining global positions of the components based on the material images; determining a target pose of the components under a target expression; and generating the sticker based on the material images, the global positions and the target pose; wherein in the sticker, an expression change of the avatar comprises a change from an initial expression to the target expression. Thus, the user only needs to input material images of a plurality of components on the avatar to generate a dynamic sticker of the avatar, thereby improving the production efficiency of the sticker and reducing the production difficulty of the sticker.

Abstract: Embodiments of the disclosure disclose a color classification method and apparatus, an electronic device and a storage medium. The color classification method including: determining, according to a first color numerical value of a color to be classified under a first color space, an initial category to which the color to be classified belongs, wherein the first color space includes a hue dimension; taking at least one sub-color category under the initial category as at least one candidate category; determining a target category of the color to be classified from the at least one candidate category according to a similarity of a second color numerical value of the color to be classified in a second color space with a third color numerical value of each of the at least one candidate category in the second color space.

Abstract: A method of generating a stylized 3D avatar is provided. The method includes receiving an input image of a user, generating, using a generative adversarial network (GAN) generator, a stylized image, based on the input image, and providing the stylized image to a first model to generate a first plurality of parameters. The first plurality of parameters include a discrete parameter and a continuous parameter. The method further includes providing the stylized image and the first plurality of parameters to a second model that is trained to generate an avatar image, receiving, from the second model, the avatar image, comparing the stylized image to the avatar image, based on a loss function, to determine an error, updating the first model to generate a second plurality of parameters that correspond to the first plurality of parameters, based on the error, and providing the second plurality of parameters as an output.

Abstract: A method of generating a style image is described. The method includes receiving an input image of a subject. The method further includes encoding the input image using a first encoder of a generative adversarial network (GAN) to obtain a first latent code. The method further includes decoding the first latent code using a first decoder of the GAN to obtain a normalized style image of the subject, wherein the GAN is trained using a loss function according to semantic regions of the input image and the normalized style image.

Abstract: The present disclosure relates to an image generation method, apparatus, and device, and a medium. The method comprises: acquiring a first image, keeping a target attribute in the first image unchanged, and editing other attributes in the first image; on the basis of the target attribute and the edited other attributes, generating a second image, so as to obtain the second image having the target attribute unchanged and other attributes changed. Therefore, the effect of quick image generation and improved image diversification of FIG. 5 can be achieved, such that during model training, the balance of training samples is improved, so as to improve the performance of the model.

Abstract: Systems and methods for rendering a translucent object are provided. In one aspect, the system includes a processor coupled to a storage medium that stores instructions, which, upon execution by the processor, cause the processor to receive at least one mesh representing at least one translucent object. For each pixel to be rendered, the processor performs a rasterization-based differentiable rendering of the pixel to be rendered using the at least one mesh and determines a plurality of values for the pixel to be rendered based on the rasterization-based differentiable rendering. The rasterization-based differentiable rendering can include performing a probabilistic rasterization process along with aggregation techniques to compute the plurality of values for the pixel to be rendered. The plurality of values includes a set of color channel values and an opacity channel value. Once values are determined for all pixels, an image can be rendered.

Abstract: The present disclosure provides a training method and device for an image identifying model, and an image identifying method. The training method comprises: obtaining image samples of a plurality of categories; inputting image samples of each category into a feature extraction layer of the image identifying model to extract a feature vector of each image sample; calculating a statistical characteristic information of an actual distribution function corresponding to each category according to the feature vector of each image sample of the each category; establishing an augmented distribution function corresponding to the each category according to the statistical characteristic information; obtaining augmented sample features of the each category based on the augmented distribution function; and inputting feature vectors of the image samples and the augmented sample features into a classification layer of the image identifying model for supervised learning.

Abstract: An image processing method and apparatus, an electronic device, and a computer-readable storage medium are provided. The image processing method includes: in response to having detected a detection object, acquiring current feature information of the detection object; acquiring limit deformation information of the target feature, wherein the limit deformation information is obtained by calculating a target virtual sub-image when the target feature is in at least one limit state; determining movement information of a feature point in an initial virtual image based on the limit deformation information and the current feature information, wherein the initial virtual image is obtained by superimposing a plurality of virtual sub-images; and driving, according to the movement information, the feature point in the initial virtual image to move, so as to generate the current virtual image corresponding to the current state.

Abstract: A method for generating a multi-dimensional stylized image. The method includes providing input data into a latent space for a style conditioned multi-dimensional generator of a multi-dimensional generative model and generating the multi-dimensional stylized image from the input data by the style conditioned multi-dimensional generator. The method further includes synthesizing content for the multi-dimensional stylized image using a latent code and corresponding camera pose from the latent space to formulate an intermediate code to modulate synthesis convolution layers to generate feature images as multi-planar representations and synthesizing stylized feature images of the feature images for generating the multi-dimensional stylized image of the input data. The style conditioned multi-dimensional generator is tuned using a guided transfer learning process using a style prior generator.

Abstract: A method is provided for evaluating an effect of classifying a fuzzy attribute of an object, the fuzzy attribute referring to an attribute, a boundary between two similar ones of a plurality of categories of which is blurred, wherein the method includes: generating a similarity-based ranked confusion matrix, which comprises: based on similarities of K categories of the fuzzy attribute of the object, ranking the K categories, where K is an integer greater than or equal to 2, generating a K×K all-zero initialization matrix, wherein an abscissa and an ordinate of the initialization matrix respectively represent predicted values and true values of the similarity-based ranked categories of the fuzzy attribute, and based on the true values and the predicted values of the category of the fuzzy attribute for the multiple object samples, updating values of corresponding elements in the initialization matrix; and displaying the similarity-based ranked confusion matrix.

Abstract: A method of generating a style image is described. The method includes receiving an input image of a subject. The method further includes encoding the input image using a first encoder of a generative adversarial network (GAN) to obtain a first latent code. The method further includes decoding the first latent code using a first decoder of the GAN to obtain a normalized style image of the subject, wherein the GAN is trained using a loss function according to semantic regions of the input image and the normalized style image.

Abstract: A method of generating a stylized 3D avatar is provided. The method includes receiving an input image of a user, generating, using a generative adversarial network (GAN) generator, a stylized image, based on the input image, and providing the stylized image to a first model to generate a first plurality of parameters. The first plurality of parameters include a discrete parameter and a continuous parameter. The method further includes providing the stylized image and the first plurality of parameters to a second model that is trained to generate an avatar image, receiving, from the second model, the avatar image, comparing the stylized image to the avatar image, based on a loss function, to determine an error, updating the first model to generate a second plurality of parameters that correspond to the first plurality of parameters, based on the error, and providing the second plurality of parameters as an output.

Abstract: Systems and methods for rendering a translucent object are provided. In one aspect, the system includes a processor coupled to a storage medium that stores instructions, which, upon execution by the processor, cause the processor to receive at least one mesh representing at least one translucent object. For each pixel to be rendered, the processor performs a rasterization-based differentiable rendering of the pixel to be rendered using the at least one mesh and determines a plurality of values for the pixel to be rendered based on the rasterization-based differentiable rendering. The rasterization-based differentiable rendering can include performing a probabilistic rasterization process along with aggregation techniques to compute the plurality of values for the pixel to be rendered. The plurality of values includes a set of color channel values and an opacity channel value. Once values are determined for all pixels, an image can be rendered.

Abstract: An image processing method includes acquiring a set of image samples for training an attribute recognition model, wherein the set of image samples includes a first subset of image samples with category labels and a second subset of image samples without category labels; training a sample prediction model using the first subset of image samples, and predicting categories of the image samples in the second subset of image samples using the trained sample prediction model; determining a category distribution of the set of image samples based on the category labels of the first subset of image samples and the predicted categories of the second subset of image samples; and acquiring a new image sample if the determined category distribution does not conform to the expected category distribution, and adding the acquired new image sample to the set of image samples.

Abstract: A method for training an image processor having a neural network model is described. A first training set of images having a first image resolution is generated. A second training set of images having a second image resolution is generated. The second image resolution is larger than the first image resolution. The neural network model of the image processor is trained using the first training set of images during a first training session. The neural network model of the image processor is trained using the second training set of images during a second training session after the first training session.

Abstract: The present disclosure relates to an image annotating method, classification method and machine learning model training method, and to the field of computer technologies. The image annotating method includes: generating an image tag vector of image to be annotated, according to a plurality of attributes for image annotating and multiple tags corresponding to each of the attributes; annotating an image category to which the image to be annotated belongs, according to vector similarity between the image tag vector and an category tag vector of each of a plurality of image categories, the category tag vector being generated according to the multiple tags corresponding to each of the attributes.

Abstract: The present disclosure relates to method, apparatus and storage medium for object attribute classification model training. There proposes a method of training a model for object attribute classification, comprising steps of: acquiring binary class attribute data related to a to-be-classified attribute on which an attribute classification task is to be performed, wherein the binary class attribute data includes data indicating whether the to-be-classified attribute is “Yes” or “No” for each of at least one class label; and pre-training the model for object attribute classification based on the binary class attribute data.

Abstract: A method is provided for evaluating an effect of classifying a fuzzy attribute of an object, the fuzzy attribute referring to an attribute, a boundary between two similar ones of a plurality of categories of which is blurred, wherein the method includes: generating a similarity-based ranked confusion matrix, which comprises: based on similarities of K categories of the fuzzy attribute of the object, ranking the K categories, where K is an integer greater than or equal to 2, generating a K×K all-zero initialization matrix, wherein an abscissa and an ordinate of the initialization matrix respectively represent predicted values and true values of the similarity-based ranked categories of the fuzzy attribute, and based on the true values and the predicted values of the category of the fuzzy attribute for the multiple object samples, updating values of corresponding elements in the initialization matrix; and displaying the similarity-based ranked confusion matrix.

Abstract: The present disclosure relates to an image attribute classification method, apparatus, electronic device, medium, and program product. The present disclosure enables inputting the image to a feature extraction network to obtain a feature map after feature extraction and N times down-sampling, wherein at least one attribute of the image occupies a second rectangular position area in the feature map after N times down-sampling; calculating a mask function of the at least one attribute of the feature map after N times down-sampling based on the second rectangular position area; obtaining a feature corresponding to the at least one attribute by dot multiplying the feature map after N times down-sampling with the mask function; and inputting the obtained feature corresponding to the at least one attribute to the corresponding attribute classifier for attribute classification.

Abstract: An image processing method includes acquiring a set of image samples for training an attribute recognition model, wherein the set of image samples includes a first subset of image samples with category labels and a second subset of image samples without category labels; training a sample prediction model using the first subset of image samples, and predicting categories of the image samples in the second subset of image samples using the trained sample prediction model; determining a category distribution of the set of image samples based on the category labels of the first subset of image samples and the predicted categories of the second subset of image samples; and acquiring a new image sample if the determined category distribution does not conform to the expected category distribution, and adding the acquired new image sample to the set of image samples.