Abstract: Computer readable medium stores a bitstream which is decodable by a decoder that is f configured to receive a bitstream, extract a header including a list of reference frames available for motion compensation, such as global motion compensation, determine, using the header, a motion model for a current block, the motion relative to a reference frame contained in the list of reference frames, and decode the current block using the motion model. Related apparatus, systems, techniques and articles are also described.

Abstract: Systems and methods for encoding and decoding video content for machine consumption with enhanced region packing strategies. An encoder includes a region detector module which receives a source video and identifies regions of interest therein. A top-down region extractor module receives the identified regions of interest and generates modified set of regions of interest that can be packed in a frame more efficiently. A region packing module receives the modified set of regions of interest and arranges the modified set of regions of interest into a packed frame in which pixels outside the modified regions of interest are substantially excluded. A video encoder encodes the packed frame and region parameters into a coded bitstream. A decoder provides complimentary processing to reconstruct a frame with the regions of interest arranged as they were in the source frame.

Abstract: Systems and methods for video encoding and decoding for machines consumption are disclosed. A decoder is provided for a decoding a bitstream encoded with a packed frame having at least on region of interest defined therein and encoded region parameters associated therewith. The decoder includes a video decoder receiving the bitstream and extracting the packed frame and region parameters. A region unpacking module receives the packed frame and region parameters and reconstructs an unpacked frame with at least one region of interest. A region padding module is provided in the decoder and applies at least one padding parameter to at least one dimension of a region of interest in the unpacked frame. The region padding may be fixed or dynamic.

Abstract: A video encoder for encoding data for machine consumption includes a region detector selection module receiving source video and detector selection parameters and selecting an object detector model. A region detection module applies a selected model to the source video to identify regions of interest in the source video. A region extractor module extracts the identified regions from the source video and a region packing module packs the extracted regions into a packed frame which excludes pixels outside the regions of interest. A video encoder receives the packed frames and data related to the region parameters required to recreate the frame and generates an encoded bitstream. The encoder and encoding methods also include region padding and region merge and region split processing. Compatible decoders and bitstreams are also provided.

Abstract: An encoder includes circuitry configured to receive a video signal and generate an encoded bitstream for decoding by a decoder which identifies, in the bitstream, a current frame, wherein the current frame includes a plurality of regions, detect, in the bitstream, an indication that a first region is encoded according to a lossless encoding protocol and another region is encoded according to a lossy encoding protocol, and decode the current frame, wherein decoding the current frame further comprises decoding the first region using a lossless decoding protocol corresponding to the lossless encoding protocol.

Abstract: A decoder includes circuitry configured to receive a bitstream; partition a current block via an exponential partitioning mode into a first region and a second region; determine a motion vector associated with the first region or the second region, the determining including constructing a candidate list; and decode the current block using the determined motion vector. Related apparatus, systems, techniques and articles are also described.

Abstract: A decoder includes circuitry configured to receive a bitstream; construct, for a current block, a motion vector candidate list including a motion vector candidate having motion information that characterizes a global motion vector; reorder the motion vector candidate list such that the motion vector candidate having the motion information that characterizes the global motion vector is first in the reordered motion vector candidate list; and reconstruct pixel data of the current block and using the reordered motion vector candidate list. Related apparatus, systems, techniques and articles are also described.

Abstract: A video coding system for machines employs adaptive quantization based on the frequency response of the machine model receiving the data. The encoder receives the machine model for the machine-based system and generates a frequency importance map from the machine model. An adjustment matrix is then generated based on the frequency importance map and is used to adjust coefficients of the default quantization matrix. The video data is quantized using the adjusted quantization matrix and encoded in a bitstream for transmission to a decoder site. At the decoder site, the decoder can extract parameters of the adjusted quantization matrix from the bitstream or calculate the adjusted quantization matrix using the machine model to inverse quantize the received data for machine consumption.

Abstract: An encoder is configured to generate an encoded bitstream that can be decoded by a decoder that is configured to receive a bitstream. The bitstream includes a picture comprising a first contiguous region of a first plurality of coding blocks and a second contiguous region comprising a second plurality of coding blocks. The first plurality of blocks having a common motion model used to decode each of the blocks of the first region and the second plurality of blocks having local motion.

Abstract: A decoder includes circuitry configured to receive a bitstream, determine whether a merge mode is enabled for a block, construct a merge candidate list including at least one candidate from a spatially non-adjacent block, at least one temporal candidate, a candidate derived from two other candidates, and a zero motion vector candidate, and reconstruct pixel data of the block and using the merge candidate list.

Abstract: A decoder includes circuitry configured to receive a bitstream, extract a header associated with a current frame and including a signal characterizing that global motion is enabled and further characterizing parameters of a global motion model, and decoding the current frame, the decoding including using a motion model for each current block having a complexity that is less than or equal to a complexity of the global motion model. Related apparatus, systems, techniques, and articles are also described.

Abstract: A video encoder s configured to encode a bitstream to be decoded by a compatible decoder, the bitstream including a coded picture with a first region with a first contiguous plurality of coded blocks and signaling information associated with each coded block. For each coded block in the first region, in response to the associated signaling information, the decoder receiving the bitstream constructs a motion vector candidate list including a motion vector candidate enabling the reconstruction of global motion in the first region. If the motion vector candidate is a translational motion vector, the decoder decodes the blocks in the first region using translational motion compensation to reconstruct global motion in the first region. If the one motion vector candidate comprises multiple control point motion vectors, the decoder uses affine motion compensation to reconstruct global motion in the first region.

Abstract: A decoder includes circuitry configured to receive a bitstream; construct, for a current block, a motion vector candidate list including a motion vector candidate having motion information that characterizes a global motion vector; reorder the motion vector candidate list such that the motion vector candidate having the motion information that characterizes the global motion vector is first in the reordered motion vector candidate list; and reconstruct pixel data of the current block and using the reordered motion vector candidate list. Related apparatus, systems, techniques and articles are also described.

Abstract: A video encoder is configured to encode a bit stream including a coded picture having a first contiguous region and a second contiguous region, the first contiguous region containing common motion, the second contiguous region containing local motion. The encoded bitstream is provided to a decoder which is configured to decode the first contiguous region of the coded picture to reconstruct the common motion by utilizing a motion model common to all of the coding blocks in the first region. A merge candidate list is selectively created and a merge candidate is selected to decode the first region based on the common motion model. The second contiguous region is decoded using individual motion information for each coding block in the second contiguous region.

Abstract: An encoder is configured to generate an encoded bitstream that can be decoded by a decoder that is configured to receive a bitstream. The bitstream includes a picture comprising a first contiguous region of a first plurality of coding blocks and a second contiguous region comprising a second plurality of coding blocks. The first plurality of blocks having a common motion model used to decode each of the blocks of the first region and the second plurality of blocks having local motion.

Abstract: A decoder includes circuitry configured to receive a bitstream, determine whether a merge mode is enabled for a block, construct a merge candidate list including adding a non-adjacent diagonal spatial candidate to the merge candidate list, and reconstruct pixel data of the block and using the merge candidate list. Related apparatus, systems, techniques and articles are also described.

Abstract: A system for coding and decoding of signals, such as pictures and video, intended for machine use is disclosed. An encoder implements a method for kernel-based transformation of the signal samples that reduces and preferably minimizes entropy of the input signal yet is equivalent to the input signal for the intended machine operation. As a result, the transformed signal sample can be compressed using fewer bits than the original. The encoded signal is received by a complimentary decoder and decoded for machine use.

Abstract: An encoder configured to encode a video bitstream for decoding by a compliant decoder configured to receive the bitstream, the encoded bitstream including a reference picture and a current picture including a coded current block, the bitstream also including an index useful for determining a scaling factor. The decoder determines that a mode when a reference picture and a current picture have different resolutions is enabled. Utilizing the mode, the decoder reconstructs the coded current block encoded by the encoder by determining a scaling factor using information in the bitstream including the index, determining a scaled prediction block by scaling a block of the reference picture using the scaling factor and by applying a pixel interpolation filter determined specifically for the prediction block and combining the scaled prediction block with a residual.

Abstract: An encoder configured to generate an encoded bitstream for decoding by a compatible decoder, wherein the decoder receives the encoded bitstream with a current picture including a current block having a first partition boundary partitioning the block into first and second non-rectangular regions and a second partition boundary, intersecting the first partition boundary, and partitioning the second non-rectangular region into three portions. Using the encoded bitstream, the decoder determines a first predictor for use within the first non-rectangular region using a first motion vector selected from a first list of motion vector candidates, determines a second predictor for use within the second non-rectangular region using a second motion vector selected from a second list of motion vector candidates; and decodes the current block using the first predictor and the second predictor. Decoding further includes smoothing the first predictor and the second predictor across the first partition boundary.

Abstract: A video signal processor is provided, having an inverse quantizer, an inverse transform processor, an in-loop filter; and a decoded picture buffer. The video signal processor is configured to receive a video signal including a picture comprising quantized pixels, wherein the picture includes a first region and a second region. The first region comprising a first plurality of blocks and having a first quantization parameter based on a first average measure of spatial activity information of the first plurality of blocks; and a second region comprising a second plurality of blocks and having a second quantization parameter based on a second average measure of information of the second plurality of blocks. The inverse quantizer being configured to inverse quantize the pixels of the blocks comprising the first region using the first quantization parameter and inverse quantize the pixels of the blocks comprising the second region using the second quantization parameter.