An image processing device includes a processor configured to: extract pixel blocks; detect pixels having a maximum value and a minimum value in each of the pixel blocks; calculate reference value candidates from the maximum and the minimum values; calculate an absolute difference value relative to each of the maximum value, the minimum value, and the reference value candidates; divide each of the pixel blocks into subblocks; select, as a reference value from among the reference value candidates in each of the subblocks, a reference value candidate close to the pixel values in which the pixels included in each of the subblocks are distributed; extract a closest difference value, the minimum value, and the reference value; quantize each of the closest difference values into a quantization value by using the difference value that is the largest from among the closest difference values; and code the quantization value.

Circuity for executing operations is provided. The operations divide a picture into tiles. The tiles are coded to generate pieces of coded data, each of which corresponds to a different one of the tiles. A bitstream is generated to include the pieces of coded data. In this regard, the coding of the tiles includes generating a first code string by: coding a first tile with reference to coding information of an already-coded tile neighboring the first tile when a boundary between the first and already-coded tiles is a first boundary; and coding the first tile without reference to the coding information of the already-coded tile when the boundary between the first and already-coded tiles is a second boundary. The bitstream is generated to include tile boundary independence information, which indicates whether each boundary between the tiles is one of the first and second boundaries.

Methods and apparatus for compressing image data are described along with corresponding methods and apparatus for decompressing the compressed image data. A decoder unit identifies neighbouring pixels based on coordinates of a sample position and fetches encoded data from the compressed image data for each of the neighbouring pixels. A first decoder decodes fetched encoded blocks of a first image and a difference decoder decodes fetched encoded sub-blocks of differences between the first image and a second image and outputs a difference quad and a prediction value for each of the four pixels, and a reconstruction of the image is generated at the sample position using the decoded blocks of the first image, difference quads and prediction values.

Methods and apparatus for compressing image data are described along with corresponding methods and apparatus for decompressing the compressed image data. A decoder unit identifies neighbouring pixels based on coordinates of a sample position and fetches encoded data from the compressed image data for each of the neighbouring pixels. A first decoder decodes fetched encoded blocks of a first image and a difference decoder decodes fetched encoded sub-blocks of differences between the first image and a second image and outputs a difference quad and a prediction value for each of the four pixels, and a reconstruction of the image is generated at the sample position using the decoded blocks of the first image, difference quads and prediction values. A bilinear filtering unit performs bilinear filtering on a linearly interpolated output of a pre-filter using a second part of the coordinates of the sample position to generate the reconstruction of the image at the sample position.

Provided is a learning device of a neural network including a bitwidth reducing unit, a learning unit, and a memory. The bitwidth reducing unit executes a first quantization that applies a first quantization area to a numerical value to be calculated in a neural network model. The learning unit performs learning with respect to the neural network model to which the first quantization has been executed. The bitwidth reducing unit executes a second quantization that applies a second quantization area to a numerical value to be calculated in the neural network model on which learning has been performed in the learning unit. The memory stores the neural network model to which the second quantization has been executed.

Methods and apparatus for compressing image data are described along with corresponding methods and apparatus for decompressing the compressed image data. A decoder unit samples compressed image data including interleaved blocks of data encoding a first image and blocks of data encoding differences between the first image and a second image, the second image being twice the width and the height of the first image. A difference decoder decodes a fetched encoded sub-block of the differences between the first and second images and output a difference quad and a prediction value for a pixel, and a filter sub-unit generates a reconstruction of the image at a sample position using decoded blocks of the first image, the difference quad and the prediction value.

Systems and methods are provided for encoding a frame of 3D media content. The systems and methods may be configured to access a first frame of 3D media content and generate a data structure for the first frame based on color attributes information of the first frame, wherein each element of the data structure encodes a single color. The systems and methods may be configured to train a machine learning model based on the first frame of 3D media content, wherein the machine learning model is trained to receive as input a coordinate of a voxel of the first frame, and to output an identifier of a particular element in the generated data structure. The systems and methods may be configured to generate encoded data for the first frame based at least in part on weights of the trained machine learning model and the generated data structure.

The present disclosure relates to a class-agnostic object segmentation system that automatically detects, segments, and selects objects within digital images irrespective of object semantic classifications. For example, the object segmentation system utilizes a class-agnostic object segmentation neural network to segment each pixel in a digital image into an object mask. Further, in response to detecting a selection request of a target object, the object segmentation system utilizes a corresponding object mask to automatically select the target object within the digital image. In some implementations, the object segmentation system utilizes a class-agnostic object segmentation neural network to detect and automatically select a partial object in the digital image in response to a target object selection request.

Methods for lossy and lossless pre-processing of image data. In one embodiment, a method for lossy pre-processing image data, where the method may include, at a computing device: receiving the image data, where the image data includes a model having a mesh, the mesh includes vertices defining a surface, the vertices including attribute vectors, and the attribute vectors including values. The method also including quantizing the values of the attribute vectors to produce modified values, where a precision of the modified values is determined based on a largest power determined using a largest exponent of the values, encoding pairs of the modified values into two corresponding units of information. The method also including, for each pair of the pairs of the modified values, serially storing the two corresponding units of information as a data stream into a buffer, and compressing the data stream in the buffer.

Circuity for executing operations is provided. The operations divide a picture into tiles. The tiles are coded to generate pieces of coded data, each of which corresponds to a different one of the tiles. A bitstream is generated to include the pieces of coded data. In this regard, the coding of the tiles includes generating a first code string by: coding a first tile with reference to coding information of an already-coded tile neighboring the first tile when a boundary between the first and already-coded tiles is a first boundary; and coding the first tile without reference to the coding information of the already-coded tile when the boundary between the first and already-coded tiles is a second boundary. The bitstream is generated to include tile boundary independence information, which indicates whether each boundary between the tiles is one of the first and second boundaries.