An image super-resolution method includes preprocessing the low-resolution image to obtain a vertical gradient map, a horizontal gradient map, and a luminance map, which are used as three different dimensions of information to constitute a to-be-input feature map, performing size conversion on the to-be-input feature map to obtain an input feature map, performing nonlinear transformation on the input feature map to obtain an input feature map obtained after the nonlinear transformation, and performing weighted processing on the input feature map and the input feature map obtained after the nonlinear transformation, to obtain an output feature map, performing size conversion on the output feature map to obtain a residual map, and combining the low-resolution image and the residual map to obtain a high-resolution image.

An apparatus for encoding an image and an apparatus for decoding an image are presented. An image contains one or more regions. For encoding the image, the image is decomposed into one or more regions and a region is evaluated to determine whether the region meets a predetermined compressions acceptability criteria. The region is then encoded in response to the transformed and quantized region meeting the predetermined compression acceptability criteria. For decoding the image, a region of the image is selected and the selected region is decoded using metadata associated with the selected region. The metadata includes transformation quantization settings and information describing an aspect ratio used to compress the region.

According to implementations of the subject matter described herein, a solution for image rescaling is proposed. According to the solution, an input image of a first resolution is obtained. An output image of a second resolution and high-frequency information following a predetermined distribution are generated based on the input image by using a trained invertible neural network, where the first resolution exceeds the second resolution. Besides, a further input image of the second resolution is obtained. A further output image of the first resolution is generated based on the further input image and high-frequency information following the predetermined distribution by using an inverse network of the invertible neural network. This solution can downscale an original image into a visually-pleasing low-resolution image with the same semantics and also can reconstruct a high-resolution image of high quality from a low-resolution image.

A method, apparatus, and computer-readable medium for point cloud coefficient coding are provided. Transform coefficients associated with point cloud data are decomposed into set-index values and symbol-index values, the symbol index-value specifying location of the transform coefficient within a set. The decomposed transform coefficients are partitioned into one or more sets based on the set-index values and the symbol-index values. The set-index values of the partitioned transform coefficients are entropy-coded, and the symbol-index values of the partitioned transform coefficients are bypass-coded. The point cloud data is compressed based on the entropy-coded symbol-index values and the bypass-coded set-index values.

A system and method for rich content transformation are provided. The system and method allow rich content transformation to be separately processed on a client device and on a cloud-based server. The client device downsizes a rich content and transmits the downsized rich content to the cloud-based server via a network. The cloud-based server calculates function parameters based on the downsized rich content using one or more machine learning models included in the server. The calculated function parameters are transmitted to the client device via the network. The client device then applies these function parameters to the rich content on the client device to obtain the transformed rich content.

A method of processing an image of a scene including a road acquired by a vehicle-mounted camera to generate boundary data indicative of a boundary of an image region which represents an unoccupied area of the road, comprising: generating (S10) an LL sub-band image of an N.sup.th level of an (N+1)-level discrete wavelet transform, DWT, decomposition of the image by iteratively low-pass filtering and down-sampling the image N times, where N is an integer equal to or greater than one; generating (S20) a sub-band image of an (N+1).sup.th level by high-pass filtering the LL sub-band image of the N.sup.th level, and down-sampling a result of the high-pass filtering, such that the sub-band image of the (N+1).sup.th level has a pixel region having substantially equal pixel values representing the unoccupied area of the road in the image; and generating (S30) the boundary data by determining a boundary of the pixel region.

An automatic abnormal cell recognition method, the method including: 1) scanning a slide using a digital pathological scanner and obtaining a cytological slide image; 2) obtaining a set of centroid coordinates of all nuclei that is denoted as CentroidOfNucleus by automatically localizing nuclei of all cells in the cytological slide image using a feature fusion based localizing method; 3) obtaining a set of cell square region of interest (ROI) images that are denoted as ROI_images; 4) grouping all cell images in the ROI_images into different groups based on sampling without replacement, where each group contains ROW×COLUMN cell images with preset ROW and COLUMN parameters; obtaining a set of splice images; and 5) classifying all cell images in the splice image simultaneously by using the splice image as an input of a trained deep neural network; and recognizing cells classified as abnormal categories.

The invention relates to a method for compressing an input data set, wherein the coefficients in the input data set are grouped in groups of coefficients, a number of bit planes, GCLI, needed for representing each group is determined, a quantization is applied, keeping a limited number of bit planes, a prediction mechanism is applied to the GCLIs for obtaining residues, and an entropy encoding of the residues is performed. The entropy-encoded residues, and the bit planes kept allow the decoder to reconstruct the quantized data, at a minimal cost in meta-data.

Systems and methods for providing panoramic image and/or video content using multi-resolution stitching. Panoramic content may include stitched spherical (360-degree) images and/or VR video. In some implementations, multi-resolution stitching functionality may be embodied in a spherical image capture device that may include two lenses configured to capture pairs of hemispherical images. The capture device may obtain images (e.g., representing left and right hemispheres) that may be characterized by 180-degree (or greater) field of view. Source images may be combined using multi-resolution stitching methodology. Source images may be transformed to obtain multiple image components characterized by two or more image resolutions. The stitched image may be encoded using selective encoding methodology including: partitioning source images into a low resolution/frequency and a high resolution/frequency components; stitching low resolution/frequency components using coarse stitching operation, stitching high resolution/high frequency components using a refined stitch operation; combining stitched LF components and stitched HF components.

An apparatus and method for geometrically correcting a distorted input frame and generating an undistorted output frame. The apparatus includes an external memory block that stores the input frame, a counter block to compute output coordinates of the output frame for a region based on a block size of the region, a back mapping block to generate input coordinates corresponding to each of the output coordinates, a bounding module to compute input blocks corresponding to each of the input coordinates, a buffer module to fetch data corresponding to each of the input blocks, an interpolation module to interpolate data from the buffer module and a display module that receives the interpolated data for each of the regions and stitch an output image. The method includes determining the size of the output block based on a magnification data.