Qualcomm Incorporated

Hongtao Wang

Marta Karczewicz

Muhammed Zeyd Coban

Jianle Chen

Vadim Seregin

Wei-Jung Chien

Yung-Hsuan Chao

Yu Han

Han Huang

Anand Meher Kotra

Venkata Meher Satchit Anand Kotra

Alican Nalci

Auke Joris Wiggers

Dana Kianfar

Geert Van Der Auwera

Bappaditya Ray

Nan Hu

Cheng-Teh Hsieh

Chun-Chi Chen

Yan Zhang

Samuel James Eadie

A method of encoding or decoding video data includes determining a block vector for a current block of a current picture, the block vector identifying a fractional-pel position between reference samples in the current picture and having a fractional-pel resolution that is less than integer-pel resolution; generating a prediction block from reference samples in the current picture based on the fractional-pel position; and encoding or decoding the current block based on the prediction block.

Fractional-pel block vector for video coding

An example device for decoding video data includes a memory configured to store video data; and a processing system including one or more processors implemented in circuitry, the processing system being configured to: determine that a previously coded block of video data was coded using uni-prediction mode for which a bi-prediction syntax element is not assigned a value; determine that a current block of the video data is to be coded using a bi-prediction mode and that motion information of the current block is to be predicted from the previously coded block, including from the bi-prediction syntax element of the previously coded block; and in response to the bi-prediction syntax element of the previously coded block not having an assigned value, decode the current block using a substitute value for the bi-prediction syntax element.

Using substitute motion information when coding video data

An example device for filtering video data includes a memory configured to store video data; and a processing system comprising one or more processors implemented in circuitry, the processing system being configured to: apply one or more neural network processing blocks to intermediate filtered video data, each of the neural network processing blocks including a first 1×1 convolutional filter, a parametric rectified linear unit (PReLU) filter, a second 1×1 convolutional filter, and a 3×3 convolutional filter; apply additional neural network processing blocks to output of the one or more neural network processing blocks to form filtered video data; and output the filtered video data.

Reduced complexity multi-mode neural network filtering of video data

An example method includes predicting, based on a plurality of color components of a block of video data coded using joint coding of chroma residuals (JCCR), a sign of a coefficient of a plurality of coefficients of a joint residual block of the block of video data; generating, for each respective color component of the plurality of color components and based on the plurality of coefficients of the joint residual block, coefficients of a respective residual block of a plurality of residual blocks; and reconstructing, based on the plurality of residual blocks, the block of video data.

Sign prediction for multiple color components in video coding

An example device for filtering decoded video data includes a memory configured to store video data; and one or more processors implemented in circuitry and configured to: decode a picture of video data; code a value for a syntax element representing a neural network model to be used to filter a portion of the decoded picture, the value representing an index into a set of pre-defined neural network models, the index corresponding to the neural network model in the set of pre-defined neural network models; and filter the portion of the decoded picture using the neural network model corresponding to the index.

Multiple neural network models for filtering during video coding

An example device for filtering decoded video data includes a memory configured to store video data; and one or more processors implemented in circuitry and configured to: decode a block of video data to form a decoded block; apply a filter to the decoded block to form a filtered block; multiply samples of the filtered block by a scaling factor to form a refined filtered block; and combine samples of the refined filtered block with corresponding samples of the decoded block. The one or more processors may further encode the block prior to decoding the block. The one or more processors may encode or decode a value of a syntax element representing the scaling factor, e.g., in a picture header of a picture including the block.

Filtering process for video coding

An example device for filtering decoded video data includes one or more processors configured to execute a neural network filtering unit to: receive data from one or more other units of the device, the data from the one or more other units of the device being different than data for a decoded picture of video data, and wherein to receive the data from the one or more other units of the device, the one or more processors are configured to execute the neural network filtering unit to receive boundary strength data from a deblocking unit of the device; determine one or more neural network models to be used to filter a portion of the decoded picture; and filter the portion of the decoded picture using the one or more neural network models and the data from the one or more other units of the device, including the boundary strength data.

A video coder may determine a quantization parameter (QP) value for a block of video data, determine a residual coding method from a plurality of residual coding methods based on the QP value, wherein the plurality of residual coding methods include transform skip (TS) residual coding and regular residual coding, and code a residual of the block of video data using the determined residual coding method.

Residual coding selection and low-level signaling based on quantization parameter

A device for processing video data includes a memory configured to store video data and one or more processors implemented in circuitry. The one or more processors are configured to obtain unfiltered reference samples for an area of a picture of the video data. The one or more processors are configured to disable intra-reference sample smoothing of the unfiltered reference samples for chroma samples in a YUV 4:2:0 format and in a YUV 4:4:4 format. The one or more processors are further configured to generate, using intra-prediction, chroma samples of a predicted block for a block of the picture based on the unfiltered reference samples when generating the chroma components in the YUV 4:2:0 format and when generating the chroma components in the YUV 4:4:4 format.

Video coding with unfiltered reference samples using different chroma formats

A device for decoding video data can be configured to receive a syntax element indicating a maximum block size for a transform skip mode; determine a maximum block size for a block-based delta pulse code modulation (BDPCM) mode based on the syntax element; and decode block of video data based on the determined maximum block size for the BDPCM mode.

Maximum allowed block size for BDPCM mode

An example device for decoding video data includes a memory configured to store video data; and one or more processors implemented in circuitry and configured to: apply a downsampling convolutional neural network layer to a first color component of a block of video data, the first color component of the block having a first size, wherein applying the downsampling convolutional neural network layer to the first color component generates a downsampled first color component having a second size smaller than the first size; filter a second color component having the second size to form a filtered second color component; concatenate the downsampled first color component with the filtered second color component to form concatenated color components; and filter the concatenated color components to form a filtered concatenated component including a filtered downsampled first color component.

Joint-component neural network based filtering during video coding

A method of coding video data, the method comprising: reconstructing a block of the video data; and applying a Convolutional Neural Network (CNN)-based filter to the reconstructed block, wherein the CNN-based filter uses a LeakyReLU activation function.

Growing community of inventors

San Diego, CA, United States of America

Hongtao Wang