Abstract: Disclosed herein is a method of performing an arithmetic decoding for data symbols, comprising: creating a decoding table index; obtaining an upper bound value and a lower bound value of a ratio between an interval length and a point within an interval assigned to a symbol from a ROM table; obtaining initial values for a bisection search from a RAM table based on the upper bound value and the lower bound value; and searching a value of sequence in the interval, wherein the interval is determined based on the initial values.

Abstract: Disclosed herein is a method of performing an arithmetic coding for data symbols, comprising: creating an interval for each of the data symbols, the interval being represented based on a starting point and a length of the interval; updating the interval for each of the data symbols; checking whether the updated interval is included in a specific range; and renormalizing the updated interval based on a result of the checking.

Abstract: A host decoder and accelerator communicate across an acceleration interface. The host decoder receives at least part of a bitstream for video, and it manages certain decoding operations of the accelerator across the acceleration interface. The accelerator receives data from the host decoder across the acceleration interface, then performs decoding operations. For a given frame, settings based on an uncompressed frame header can be transferred in a different buffer of the acceleration interface than a compressed frame header and compressed frame data. Among other features, the host decoder can assign settings used by the accelerator that override values of bitstream syntax elements, can assign surface index values used by the accelerator to update reference frame buffers, and can handle skipped frames without invoking the accelerator. Among other features, the accelerator can use surface index values to update reference frame buffers, and can handle changes in spatial resolution at non-key frames.

Abstract: A computer-implemented method is provided for compressing a collection of images. The method includes: receiving image data for an image ensemble composed of a plurality of images; dividing the image data into a plurality of data blocks; decomposing each data block from the plurality of data blocks into a set of rank-one tensors by estimating each rank-one tensor individually, where each rank-one tensor is represented by three one-dimensional vectors; arranging the rank-one tensors for each of the plurality of data blocks into a two-dimensional matrix, where the decomposer is implemented by computer processor; compressing the two-dimensional matrix using a compression operation; and storing the compressed two-dimensional matrix in a non-transitory data store.

Abstract: Disclosed herein is a method of performing an arithmetic decoding for data symbols, comprising: creating a decoding table index; obtaining an upper bound value and a lower bound value of a ratio between an interval length and a point within an interval assigned to a symbol from a ROM table; obtaining initial values for a bisection search from a RAM table based on the upper bound value and the lower bound value; and searching a value of sequence in the interval, wherein the interval is determined based on the initial values.

Abstract: A host decoder and accelerator communicate across an acceleration interface. The host decoder receives at least part of a bitstream for video, and it manages certain decoding operations of the accelerator across the acceleration interface. The accelerator receives data from the host decoder across the acceleration interface, then performs decoding operations. For a given frame, settings based on an uncompressed frame header can be transferred in a different buffer of the acceleration interface than a compressed frame header and compressed frame data. Among other features, the host decoder can assign settings used by the accelerator that override values of bitstream syntax elements, can assign surface index values used by the accelerator to update reference frame buffers, and can handle skipped frames without invoking the accelerator. Among other features, the accelerator can use surface index values to update reference frame buffers, and can handle changes in spatial resolution at non-key frames.

Abstract: A computer-implemented method is provided for compressing a collection of images. The method includes: receiving image data for an image ensemble composed of a plurality of images; dividing the image data into a plurality of data blocks; decomposing each data block from the plurality of data blocks into a set of rank-one tensors by estimating each rank-one tensor individually, where each rank-one tensor is represented by three one-dimensional vectors; arranging the rank-one tensors for each of the plurality of data blocks into a two-dimensional matrix, where the decomposer is implemented by computer processor; compressing the two-dimensional matrix using a compression operation; and storing the compressed two-dimensional matrix in a non-transitory data store.