The present disclosure relates to an image processing apparatus and a method that enable decoding of encoded data of an octree in various processing orders. The octree corresponding to point cloud data is encoded after the context is initialized for each layer of the octree. Further, a breadth-first order or a depth-first order is selected as the decoding order for the encoded data of the octree corresponding to point cloud data, and the encoded data is decoded in the selected decoding order. The present disclosure can be applied to an image processing apparatus, an electronic apparatus, an image processing method, a program, or the like, for example.

An exemplary embodiment of the invention relates to a method of using pattern vectors for image coding and decoding. The method comprises converting a block of image data into a set of transform coefficients, quantizing the transform coefficients such that a number of the coefficients become zero, constructing a single entity or bit vector indicating which coefficients are non-zero, coding the single entity or bit vector as an integer using an adaptive, semi-adaptive or non-adaptive arithmetic coder, coding the values of the coefficients in any fixed order, using an adaptive, semi-adaptive or non-adaptive arithmetic coder, or some other coder, and coding all coefficients except the zero coefficients. The system and method of decoding data relate to the corresponding hardware and process steps performed by the decoder when decoding a bitstream coded as described herein.

A method and apparatus for performing adaptive stochastic entropy encoding and decoding are provided. Adaptive stochastic entropy encoding may include identifying a current portion of an input video stream, and identifying a current probability distribution, which may be an adapted probability distribution associated with a previously encoded portion of the video stream. Adaptive stochastic entropy encoding may include identifying a forward update probability distribution based on the current portion, generating a modified probability distribution for the current portion based on the forward update probability distribution and the current probability distribution, generating an encoded portion based on the current portion and the modified probability distribution, and generating an adapted probability distribution based on the current probability distribution and the forward update probability distribution.

In some data compression algorithms and/or standards, the compressed data comprises variable length symbols. A set of parallel decoders speculatively decode/decompress a window (i.e., sub-block) of data. Each of the decoders attempts to decode/decompress a symbol that starts at a different location in the compressed data block. Once the decoders have finished decoding a symbol (or determined that a valid symbol does not begin at the beginning of the window assigned to that decoder), a symbol strider selects the decoder outputs corresponding to valid symbols. The symbol strider successively selects decoder outputs based on the size of the previous symbols that were found to be valid. When the next valid symbol begins outside the current window, its location is stored to indicate the location of the next valid symbol in a subsequent window.

A data compression method, comprising: obtaining a plurality of values of a parameter and an occurrence probability of each of the plurality of values (S101) comparing the occurrence probability with a predetermined threshold, wherein values with the occurrence probability less than the predetermined threshold are first set of values, and values with the occurrence probability greater than or equal to the predetermined threshold are second set of values (S102), performing pretreatment on the first set of values (S103), and encoding the second set of values and the pretreated first set of values (S104). By means of the data compression method, the maximum codeword length can be effectively reduced, so as to reduce the requirements of a code table to the storage space.

A system comprises an encoder configured to entropy encode a bitstream comprising both compressible and non-compressible symbols. The encoder parses the bitstream into a compressible symbol sub-stream and a non-compressible sub-stream. The non-compressible symbol sub-stream bypass an entropy encoding component of the encoder while the compressible symbol sub-stream is entropy encoded. When a quantity of bytes of entropy encoded symbols and bypass symbols is accumulated a chunk of fixed or known size is formed using the accumulated entropy encoded symbol bytes and the bypass bytes without waiting on the full bitstream to be processed by the encoder. In a complementary manner, a decoder reconstructs the bitstream from the packets or chunks.

Systems and methods for encoding and decoding neural network data is provided. A method includes: receiving a neural network representation (NNR) bitstream including a group of NNR units (GON) that represents an independent neural network with a topology, the GON including an NNR model parameter set unit, an NNR layer parameter set unit, an NNR topology unit, an NNR quantization unit, and an NNR compressed data unit; and reconstructing the independent neural network with the topology by decoding the GON.

Methods and apparatus are provided for improved entropy encoding and decoding. An apparatus includes a video encoder (200) for encoding at least a block in a picture by transforming a residue of the block to obtain transform coefficients, quantizing the transform coefficients to obtain quantized transform coefficients, and entropy coding the quantized transform coefficients. The quantized transform coefficients are encoded using a flag to indicate that a current one of the quantized transform coefficients being processed is a last non-zero coefficient for the block having a value greater than or equal to a specified value.

There is provided a system and method for compression and decompression of a data stream used by machine learning networks. The method including: encoding each value in the data stream, including: determining a mapping to one of a plurality of non-overlapping ranges, each value encoded as a symbol representative of the range and a corresponding offset; and arithmetically coding the symbol using a probability count; storing a compressed data stream including the arithmetically coded symbols and the corresponding offsets; and decoding the compressed data stream with arithmetic decoding using the probability count, the arithmetic decoded symbols use the offset bits to arrive at a decoded data stream; and communicating the decoded data stream for use by the machine learning networks.

Methods and apparatus are provided for unified significance map coding. An apparatus includes a video encoder (400) for encoding transform coefficients for at least a portion of a picture. The transform coefficients are obtained using a plurality of transforms. One or more context sharing maps are generated for the transform coefficients based on a unified rule. The one or more context sharing maps are for providing at least one context that is shared among at least some of the transform coefficients obtained from at least two different ones of the plurality of transforms.