A method for denoising an image includes: receiving, by a processing circuit of a user equipment, an input image; supplying, by the processing circuit, the input image to a trained convolutional neural network (CNN) including a multi-scale residual dense block (MRDB), the MRDB including: a residual dense block (RDB); and an atrous spatial pyramid pooling (ASPP) module; computing, by the processing circuit, an MRDB output feature map using the MRDB; and computing, by the processing circuit, an output image based on the MRDB output feature map, the output image being a denoised version of the input image.

A method for denoising an image includes: receiving, by a processing circuit of a user equipment, an input image; supplying, by the processing circuit, the input image to a trained convolutional neural network (CNN) including a multi-scale residual dense block (MRDB), the MRDB including: a residual dense block (RDB); and an atrous spatial pyramid pooling (ASPP) module; computing, by the processing circuit, an MRDB output feature map using the MRDB; and computing, by the processing circuit, an output image based on the MRDB output feature map, the output image being a denoised version of the input image.

An electronic device and method for shape refinement of a 3D mesh reconstructed from images is disclosed. A set of images of an object is acquired and used to estimate a first 3D mesh of a head portion of the object. A first set of operations is executed on the first 3D mesh to generate a second 3D mesh. The first set of operations includes a removal of one or more regions which are unneeded for head-shape estimation and/or a removal of one or more mesh artifacts associated with a 3D shape or a topology of the first 3D mesh. A 3D template mesh is processed to determine a set of filling patches which corresponds to a set of holes in the second 3D mesh. Based on the second 3D mesh and the set of filling patches, a hole filling operation is executed to generate a final 3D mesh.

An electronic device and method for shape refinement of a 3D mesh reconstructed from images is disclosed. A set of images of an object is acquired and used to estimate a first 3D mesh of a head portion of the object. A first set of operations is executed on the first 3D mesh to generate a second 3D mesh. The first set of operations includes a removal of one or more regions which are unneeded for head-shape estimation and/or a removal of one or more mesh artifacts associated with a 3D shape or a topology of the first 3D mesh. A 3D template mesh is processed to determine a set of filling patches which corresponds to a set of holes in the second 3D mesh. Based on the second 3D mesh and the set of filling patches, a hole filling operation is executed to generate a final 3D mesh.

A selection apparatus capable of efficiently selecting an optimum setting condition for filtering is provided. The selection apparatus is an apparatus that selects a setting condition for filtering to be performed on a reading target. The selection apparatus includes: a determiner that determines whether the reading target is readable with each of a plurality of combinations selected from among combinations of all setting conditions for at least two types of filtering; and a selector that selects a setting condition for the filtering based on a result of the determination by the determiner.

A selection apparatus capable of efficiently selecting an optimum setting condition for filtering is provided. The selection apparatus is an apparatus that selects a setting condition for filtering to be performed on a reading target. The selection apparatus includes: a determiner that determines whether the reading target is readable with each of a plurality of combinations selected from among combinations of all setting conditions for at least two types of filtering; and a selector that selects a setting condition for the filtering based on a result of the determination by the determiner.

An image processing method includes: performing target object detection on an initial image to obtain an object detection result, and performing image saliency detection on the initial image to obtain a saliency detection result; cropping the initial image based on the object detection result and the saliency detection result to obtain a corresponding cropped image; acquiring an image template for indicating an image style, and acquiring layer information corresponding to the image template; and adding the layer information to the cropped image based on the image template to obtain a target image corresponding to the image style indicated by the image template.

An image processing method includes: performing target object detection on an initial image to obtain an object detection result, and performing image saliency detection on the initial image to obtain a saliency detection result; cropping the initial image based on the object detection result and the saliency detection result to obtain a corresponding cropped image; acquiring an image template for indicating an image style, and acquiring layer information corresponding to the image template; and adding the layer information to the cropped image based on the image template to obtain a target image corresponding to the image style indicated by the image template.

A neural network training method, an image processing method, and apparatuses thereof are provided. The neural network training method includes obtaining a first domain image and a second domain image, where the first domain image and the second domain image are unpaired images in different domains; obtaining a scaled first domain image by scaling, at an iteration, the first domain image; obtaining a training patch by cropping the scaled first domain image, where each training patch has a same number of pixels with different contents; inputting the training patch into the neural network at the iteration, and outputting an output patch; calculating a contrastive loss based on a query sub-patch and negative sub-patches selected from the training patch and a corresponding positive sub-patch selected from the output patch; and updating model parameters of the neural network based on the contrastive loss and a generative adversarial network loss.

A neural network training method, an image processing method, and apparatuses thereof are provided. The neural network training method includes obtaining a first domain image and a second domain image, where the first domain image and the second domain image are unpaired images in different domains; obtaining a scaled first domain image by scaling, at an iteration, the first domain image; obtaining a training patch by cropping the scaled first domain image, where each training patch has a same number of pixels with different contents; inputting the training patch into the neural network at the iteration, and outputting an output patch; calculating a contrastive loss based on a query sub-patch and negative sub-patches selected from the training patch and a corresponding positive sub-patch selected from the output patch; and updating model parameters of the neural network based on the contrastive loss and a generative adversarial network loss.