Abstract: A system comprises an encoder configured to compress attribute information and/or spatial information for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. The encoder is configured to convert a point cloud into an image based representation. The encoder packs patch images into an image frame and fills empty spaces in the image frame with a padding. Various compression strategies may be used to encode an occupancy map and related block-to-patch information indicating which portions of the image frame correspond to which packed patches. Packed image frames comprising patches and padding, along with an encoded occupancy map and related block-to-patch information are sent to a decoder. The decoder is configured to generate a decompressed point cloud based on the packed image frames, compressed occupancy map, and related block-to-patch information.

Abstract: Systems and methods disclosed for video compression, utilizing neural networks for predictive video coding. Processes employed combine multiple banks of neural networks with codec system components to carry out the coding and decoding of video data.

Abstract: A first aspect is a method for coding a group of pictures (GOP) that includes frames of a video. The method includes encoding, at least some of the frames of the GOP, using a first encoding pass to obtain encoding statistics; obtaining, using the encoding statistics, respective temporal dependency likelihoods (TDLs) for the at least some of the frames of the GOP, where the respective TDLs indicate contributions that the at least some of the frames make in reducing prediction errors of the GOP; obtaining a reference frame based on the respective TDLs; and using the reference frame in encoding at least some of the frames of the GOP in a second encoding pass.

Abstract: A system comprises an encoder configured to compress attribute information and/or spatial for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. To compress the attribute and/or spatial information, the encoder is configured to convert a point cloud into an image based representation. Also, the decoder is configured to generate a decompressed point cloud based on an image based representation of a point cloud. A block/sub-block organization scheme is used to encode blocks and sub-blocks of an occupancy map used in compressing the point cloud. Binary values are assigned to blocks/sub-blocks based on whether they contain patches projected on the point cloud. A traversal path is chosen that takes advantage of run-length encoding strategies to reduce a size of an encoded occupancy map. Also, auxiliary information is used to further improve occupancy map compression.

Abstract: A first aspect is a method for coding a group of pictures (GOP) that includes frames of a video. The method includes encoding, at least some of the frames of the GOP, using a first encoding pass to obtain encoding statistics; obtaining, using the encoding statistics, respective temporal dependency likelihoods (TDLs) for the at least some of the frames of the GOP, where the respective TDLs indicate contributions that the at least some of the frames make in reducing prediction errors of the GOP; obtaining a reference frame based on the respective TDLs; and using the reference frame in encoding at least some of the frames of the GOP in a second encoding pass.

Abstract: An encoder is configured to compress point cloud geometry information using an octree geometric compression technique that utilizes a binary arithmetic encoder, a look-ahead table, a cache, and a context selection process, wherein encoding contexts are selected based, at least in part, on neighborhood configurations. In a similar manner, a decoder is configured to decode compressed point cloud geometry information utilizing a binary arithmetic encoder, a look-ahead table, a cache, and a context selection process.

Abstract: Techniques for video exchange are disclosed in which a video source sends redundant copies of video coded at a given presentation time. A decoder may determine, from metadata stored with a first decoded frame, whether other decoded frames have been designated as correlated to the first decoded frame. If so, the decoder may fetch other decoding frames using time indicator values of other decoded frames in metadata stored with the first decoded frame. When other decoded frame(s) are found, the decoder may blend content of the first coded frame and the other decoded frame(s). The decoder may render the blended frame. When one such coded frame is an intra-coded frame, the proposed technique may alleviate beating artifacts by blending recovered data of the intra-coded frame with recovered data of another frame, which may be inter-coded.

Abstract: Video compression and decompression techniques are disclosed that provide improved bandwidth control for video compression and decompression systems. In particular, video coding and decoding techniques quantize input video in multiple dimensions. According to these techniques, pixel residuals may be generated from a comparison of an array of input data to an array of prediction data. The pixel residuals may be quantized in a first dimension. After the quantization, the quantized pixel residuals may be transformed to an array of transform coefficients. The transform coefficients may be quantized in a second dimension and entropy coded. Decoding techniques invert these processes. In still other embodiments, multiple quantizers may be provided upstream of the transform stage, either in parallel or in cascade, which provide greater flexibility to video coders to quantize data in different dimensions in an effort to balance the competing interest in compression efficiency and quality of reconstructed video.

Abstract: A system comprises an encoder configured to compress attribute information and/or spatial for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. To compress the attribute and/or spatial information, the encoder is configured to convert a point cloud into an image based representation. Also, the decoder is configured to generate a decompressed point cloud based on an image based representation of a point cloud. The encoder is configured project the point cloud on to patch planes to compress the point cloud, and supports multiple layered patch planes. For example, some point clouds may have a depth, and points at different depths may be assigned to different layered patch planes.

Abstract: A system comprises an encoder configured to compress attribute information for a point cloud and/or a decoder configured to decompress compressed attribute information. Attribute values for at least one starting point are included in a compressed attribute information file and attribute correction values are included in the compressed attribute information file. Attribute values are predicted based, at least in part, on attribute values of neighboring points. The predicted attribute values are compared to attribute values of a point cloud prior to compression to determine attribute correction values. In order to improve computing efficiency and/or repeatability, fixed-point number representations are used when determining predicted attribute values and attribute correction values. A decoder follows a similar prediction process as an encoder and corrects predicted values using attribute correction values included in a compressed attribute information file using fixed-point number representations.

Abstract: A system comprises an encoder configured to compress attribute and/or spatial information for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. To compress the attribute and/or spatial information, the encoder is configured to convert a point cloud into an image based representation. Also, the decoder is configured to generate a decompressed point cloud based on an image based representation of a point cloud. In some embodiments, an encoder performs downscaling of an image frame prior to video encoding and a decoder performs upscaling of an image frame subsequent to video decoding.

Abstract: A system comprises an encoder configured to compress attribute information for a point cloud and/or a decoder configured to decompress compressed attribute information for the point cloud. To compress the attribute information, multiple levels of detail are generated based on an ordering of the points according to a space filling curve and attribute values are predicted. The attribute values may be predicted simultaneously while points are being assigned to different levels of detail. A decoder follows a similar prediction process based on level of details. Also, attribute correction values may be determined to correct predicted attribute values and may be used by a decoder to decompress a point cloud compressed using level of detail attribute compression. In some embodiments, attribute correction values may take into account an influence factor of respective points in a given level of detail on attributes in other levels of detail.

Abstract: Systems and methods disclosed for video compression, utilizing neural networks for predictive video coding. Processes employed combine multiple banks of neural networks with codec system components to carry out the coding and decoding of video data.

Abstract: Techniques are disclosed by which a coding parameter is determined to encode video data resulting in encoded video data possessing a highest possible video quality. Features may be extracted from an input video sequence. The extracted features may be compared to features described in a model of coding parameters generated by a machine learning algorithm from reviews of previously-coded videos, extracted features of the previously-coded videos, and coding parameters of the previously-coded videos. When a match is detected between the extracted features of the input video sequence and extracted features represented in the model, a determination may be made as to whether coding parameters that correspond to the matching extracted feature correspond to a tier of service to which the input video sequence is to be coded.

Abstract: A system comprises an encoder configured to compress attribute information and/or spatial for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. To compress the attribute and/or spatial information, the encoder is configured to convert a point cloud into an image based representation. Also, the decoder is configured to generate a decompressed point cloud based on an image based representation of a point cloud.

Abstract: A system comprises an encoder configured to compress attribute and/or spatial information for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. To compress the attribute and/or spatial information, the encoder is configured to convert a point cloud into an image based representation. Also, the decoder is configured to generate a decompressed point cloud based on an image based representation of a point cloud. In some embodiments, an encoder performs downscaling of an image frame prior to video encoding and a decoder performs upscaling of an image frame subsequent to video decoding.

Abstract: A method of adaptive chroma downsampling is presented. The method comprises converting a source image to a converted image in an output color format, applying a plurality of downsample filters to the converted image and estimating a distortion for each filter chose the filter that produces the minimum distortion. The distortion estimation includes applying an upsample filter, and a pixel is output based on the chosen filter. Methods for closed loop conversions are also presented.

Abstract: Methods and systems for improving coding efficiency of video.

Abstract: Techniques are disclosed by which a coding parameter is determined to encode video data resulting in encoded video data possessing a highest possible video quality. Features may be extracted from an input video sequence. The extracted features may be compared to features described in a model of coding parameters generated by a machine learning algorithm from reviews of previously-coded videos, extracted features of the previously-coded videos, and coding parameters of the previously-coded videos. When a match is detected between the extracted features of the input video sequence and extracted features represented in the model, a determination may be made as to whether coding parameters that correspond to the matching extracted feature correspond to a tier of service to which the input video sequence is to be coded.

Abstract: Video compression and decompression techniques are disclosed that provide improved bandwidth control for video compression and decompression systems. In particular, video coding and decoding techniques quantize input video in multiple dimensions. According to these techniques, pixel residuals may be generated from a comparison of an array of input data to an array of prediction data. The pixel residuals may be quantized in a first dimension. After the quantization, the quantized pixel residuals may be transformed to an array of transform coefficients. The transform coefficients may be quantized in a second dimension and entropy coded. Decoding techniques invert these processes. In still other embodiments, multiple quantizers may be provided upstream of the transform stage, either in parallel or in cascade, which provide greater flexibility to video coders to quantize data in different dimensions in an effort to balance the competing interest in compression efficiency and quality of reconstructed video.