Systems, devices, and methods for performing feature compression, including obtaining an input video; obtaining a feature map corresponding to the input video, the feature map including a plurality of feature channels; reordering the plurality of feature channels based on at least one characteristic of the plurality of feature channels; compressing the reordered plurality of feature channels; and generating an encoded bitstream based on the compressed and reordered plurality of feature channels.

Systems, devices, and methods for performing feature compression, including obtaining an input video; obtaining a feature map corresponding to the input video, the feature map including a plurality of feature channels; reordering the plurality of feature channels based on at least one characteristic of the plurality of feature channels; compressing the reordered plurality of feature channels; and generating an encoded bitstream based on the compressed and reordered plurality of feature channels.

A three-dimensional data encoding method including; generating a layered structure including one or more layers by hierarchically arranging three-dimensional points each having an attribute information item; encoding the attribute information item of each of the three-dimensional points using the layered structure; and generating a first bitstream including the attribute information item encoded and an identification information item indicating whether the three-dimensional points used in the hierarchical arranging are re-ordered in Morton order before the hierarchical arranging.

A three-dimensional data encoding method including; generating a layered structure including one or more layers by hierarchically arranging three-dimensional points each having an attribute information item; encoding the attribute information item of each of the three-dimensional points using the layered structure; and generating a first bitstream including the attribute information item encoded and an identification information item indicating whether the three-dimensional points used in the hierarchical arranging are re-ordered in Morton order before the hierarchical arranging.

Different implementations are described, particularly implementations for video encoding and decoding based on wherein the partitioning tree structure is partially shared between luma and chroma blocks are presented. According to an implementation, a single partitioning tree structure is shared between luma and chroma blocks from a root node of the partitioning tree down to a switching node and a dual partitioning tree structure is determined for luma and chroma blocks from the switching node down to a leaf node of the partitioning tree. Thus, this implementation optimizes the coding efficiency by allowing separated trees for smaller blocks, while limiting the complexity of decoding pipeline.

Different implementations are described, particularly implementations for video encoding and decoding based on wherein the partitioning tree structure is partially shared between luma and chroma blocks are presented. According to an implementation, a single partitioning tree structure is shared between luma and chroma blocks from a root node of the partitioning tree down to a switching node and a dual partitioning tree structure is determined for luma and chroma blocks from the switching node down to a leaf node of the partitioning tree. Thus, this implementation optimizes the coding efficiency by allowing separated trees for smaller blocks, while limiting the complexity of decoding pipeline.

This disclosure is directed to systems and methods of streaming extensions for video encoding. The streaming extensions may enable the bitstream syntax for layered video data to be modified to reduce overhead for encoding. The bitstream syntax may be modified to enable variable length luma and chroma components, and enable the alignment between the layers and slice to be bit aligned to enable increased granularity in image encoding, and to minimize overhead between different elements within the layers.

An encoder includes circuitry and memory coupled to the circuitry. In operation, the circuitry: encodes one or more pictures which have common time information and each of which is included in a different layer; adds the one or more pictures into one access unit in a bitstream; and adds, into the bitstream, a first flag indicating that a total number of access units present in the bitstream is one.

An encoder includes circuitry and memory coupled to the circuitry. In operation, the circuitry: encodes one or more pictures which have common time information and each of which is included in a different layer; adds the one or more pictures into one access unit in a bitstream; and adds, into the bitstream, a first flag indicating that a total number of access units present in the bitstream is one.

Techniques and tools for reducing latency in video encoding and decoding by constraining latency due to reordering of video frames, and by indicating the constraint on frame reordering latency with one or more syntax elements that accompany encoded data for the video frames. For example, a real-time communication tool with a video encoder sets a syntax element that indicates a constraint on frame reordering latency, which is consistent with inter-frame dependencies between multiple frames of a video sequence, then outputs the syntax element. A corresponding real-time communication tool with a video decoder receives the syntax element that indicates the constraint on frame reordering latency, determines the constraint on frame reordering latency based on the syntax element, and uses the constraint on frame reordering latency to determine when a reconstructed frame is ready for output (in terms of output order).