Qualcomm Incorporated

Nokia Corporation

Nokia Mobile Phones Limited

Velos Media, LLC

Shumaker & Sieffert, P.a.

Other

Nokia Technologies Oy

Velos Media International Limited

Marta Karczewicz

Vadim Seregin

Wei-Jung Chien

Jianle Chen

Li Feng Zhang

Geert Van Der Auwera

Rajan Laxman Joshi

Joel Sole Rojals

Muhammed Zeyd Coban

Adarsh Krishnan Ramasubramonian

Ying Hai Chen

Xianglin Wang

Xiang Yang Li

Han Huang

Xin Zhao

Peisong Chen

Bappaditya Ray

Liwei Guo

Dmytro Rusanovskyy

Krishnakanth Rapaka

Wei Pu

Nan Hu

Yan Ye

Luong Pham Van

Amir Said

In Suk Chong

Hilmi Enes Egilmez

Kai Zhang

Hsiao-Chiang Chuang

Yi-Wen Chen

Cheng-Teh Hsieh

Chun-Chi Chen

Hongtao Wang

Ye-Kui Wang

Feng Zou

Yunfei Zheng

Chao Pang

Yao-Jen Chang

Sungwon Lee

Yung-Hsuan Chao

Louis Joseph Kerofsky

Yu Han

Yan Zhang

Done Bugdayci Sansli

Yu-Chen Sun

Hongbin Liu

Woo-Shik Kim

Zhi Zhang

Alican Nalci

Chengjie Tu

Jani Lainema

Vijayaraghavan Thirumalai

Rahul P Panchal

Kevin Pascal Andre Reuze

Jie Dong

Yuriy Reznik

Yong He

Yang Yu

Bogdan-Paul Dobrin

Fnu Hendry

Ossi Kalevo

Chao-Hsiung Hung

Hyukjune Chung

Jewon Kang

Jaehong Chon

Ragip Kurceren

Rong Zhang

Keming Cao

Xiang Li

Anand Meher Kotra

Giovanni Motta

Sanjeev Kumar

Justin Ridge

Akshay Gadde

Thibaud Laurent Biatek

Venkata Meher Satchit Anand Kotra

Ankitesh Kumar Singh

Antti Hallapuro

Yong Wang

Nikolai Konrad Leung

Kai Wang

Shu Xiao

Auke Joris Wiggers

Jacek Nieweglowski

Emre Baris Aksu

Li Zhang

Tao Wang

Natan Jacobson

Andrew Edmund Turner

Phoom Sagetong

Seyfullah Halit Oguz

Po-Han Lin

Yekui Wang

Amit Rohatgi

Prasanjit Panda

Viktor Varsa

Guoxin Jin

A G-PCC coder may determine an occupancy of a reference child node in a reference node, wherein the reference node is in a reference frame of point cloud data used for inter prediction of a current node in a current frame of the point cloud data. The G-PCC coder may further determine a context for decoding a current occupancy bit of a current child node of the current node based on the occupancy of the reference child node, and arithmetic decode the current occupancy bit using the context.

Occupancy coding using inter prediction with octree occupancy coding based on dynamic optimal binary coder with update on the fly (OBUF) in geometry-based point cloud compression

A device for decoding a bitstream that includes point cloud data can be configured to determine, based on syntax signaled in the bitstream, that in-tree quantization is enabled for a node; determine, for the node based on the syntax signaled in the bitstream, that an angular mode is activated for the node; in response to in-tree quantization being enabled for the node, determine for the node a quantized value representing a coordinate position relative to an origin position; scale the quantized value without clipping to determine a scaled value representing the coordinate position relative to the origin position; and determine a context for context decoding a plane position syntax element for the angular mode based on the scaled value representing the coordinate position relative to the origin position.

Angular mode and in-tree quantization in geometry point cloud compression

An example device for coding point cloud data includes a memory configured to store point cloud data; and one or more processors implemented in circuitry and configured to: determine at least one of 1) that a node of an octree of the point cloud data is not inter predictable or 2) that angular mode is enabled for the node; in response to determining the at least one of 1) that the node is not inter predictable or 2) that angular mode is enabled for the node, determine an inferred direct coding mode (IDCM) mode for the node; and code occupancy data of the node using the determined IDCM mode.

Coding point cloud data using direct mode for inter-prediction in G-PCC

A device for encoding or decoding point cloud data may be configured to, responsive to determining to predict a current point in a current frame using an inter prediction mode: identify a reference frame; derive one or more motion compensated reference points from the reference frame; selectively resample points in the reference frame based on the one or more motion compensated reference points to generate a resampled reference frame; and inter predict the current point in the current frame based on the resampled reference frame.

Inter prediction coding for geometry point cloud compression

Encoding and decoding video data using an affine decoder side motion vector derivation (DMVR) mode includes receiving a block of video data to be decoded using the affine DMVR mode, and dividing the block into a plurality of subblocks. A video encoder and video decoder may determine a final offset for the affine DMVR mode using a first subset of the plurality of subblocks. The video encoder and decoder may code the block of video data using the final offset to generate a coded block of video data.

Methods of subblock skipping for affine motion search for video coding

An example device for decoding video data includes one or more processors configured to: determine that a first weight and a second weight are specified for a bi-prediction mode predicted current block of video data; determine whether the current block is to be predicted using multi-hypothesis prediction (MHP) mode with the bi-prediction mode as a base mode; in response to determining that the current block is to be predicted using the MHP mode with the bi-prediction mode as the base mode, determine an additional inter-prediction mode of the MHP mode; generate a first prediction block according to the bi-prediction mode; generate a second prediction block according to the additional inter-prediction mode; generate a final prediction block for the current block according to the MHP mode using the first prediction block and the second prediction block; and decode the current block using the final prediction block.

Multiple hypothesis prediction for video coding

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 device for coding video data includes memory configured to store the video data and one or more processors communicatively coupled to the memory. The one or more processors are configured to reduce a bit length of one or more input variables for a linear regression operation to generate one or more reduced bit length input variables, the input variables including at least one of a) one or more delta coordinates, b) one or more delta motion vectors, or c) a value representing a number of subblocks. The one or more processors are configured to perform the linear regression operation and derive an affine motion model based on the performing the linear regression on the one or more reduced bit length input variables. The one or more processors are configured to code a current block of the video data based on the affine motion model.

Bit-length control for linear regression-based affine merge candidate derivation

A method of encoding a point cloud includes determining, by one or more processors, a quantity of lasers used to capture light detection and ranging (LIDAR) data that represents the point cloud; and encoding, by the one or more processors, a laser index for a current node of the point cloud, wherein encoding the laser index comprises: obtaining a predicted laser index value of the current node; determining a residual laser index value for the current node, wherein determining the residual laser index value comprises constraining a sum of the residual laser index value and the predicted laser index value to be less than or equal to the determined quantity of lasers minus one; and encoding, in a bitstream, one or more syntax elements that represent the residual laser index value.

Clipping laser indices in predictive geometry coding for point cloud compression

A method of encoding or decoding video data includes constructing a list of chroma intra-prediction modes for a chroma block of a current block of the video data, wherein constructing includes adding intra-prediction modes of a first group to the list of chroma intra-prediction modes, the first group comprising two or more intra-prediction modes derived from intra-prediction modes of two or more co-located luma blocks of the current block that are co-located with the chroma block; determining an intra-prediction mode for the chroma block from the list of chroma intra-prediction modes; and encoding or decoding the chroma block based on the intra-prediction mode.

Intra chroma mode list construction for video coding

A video coder is configured to construct a merge candidate list of merge candidates, wherein the merge candidate list has N1 candidates, N1 being a positive integer value, reorder the merge candidates in the merge candidate list to create a reordered merge candidate list, reduce the reordered merge candidate list to create an output merge candidate list, wherein the output merge candidate list has N2 candidates, wherein N2 is less than N1, and code a block of video data using the output merge candidate list.

Merge candidate reordering in video coding

An example device includes memory configured to store the point cloud data and one or more processors configured to determine a first point of the point cloud data to be a first node of a first prediction tree branch. The one or more processors are configured to determine that a first azimuth difference between the first point and a second point of the point cloud data does not meet a first azimuth threshold, and based on that determination, determine the second point to be a second node of the first prediction tree branch. The one or more processors are configured to determine that a second azimuth difference between a third point of the point cloud data and a fourth point of the point cloud data meets the first azimuth threshold and based on that determination, determine the fourth point to be a first node of a second prediction tree branch.

Predictive geometry coding of point cloud

A method for coding a block of video data using affine mode includes determining a refined affine model for the current block of video data from a linear regression process using a base motion vector field and a guidance motion vector field as inputs to the linear regression process. The method further includes determining affine merge candidates for the current block using the refined affine model, and coding the current block of video data using the affine merge candidates.

Derivation of affine merge candidates with linear regression for video coding

A method of processing a point cloud includes determining that angular mode is enabled for encoding or decoding a current point of points in the point cloud, and parsing or signaling information for an azimuthal angle residual value for the current point independent of a radius value of the current point or a radius value of a previous point of the point cloud that is previous to the current point in decoding order. The azimuthal angle residual value is based on a difference between an azimuthal angle value of the current point and a predictor azimuthal angle value of the current point, and the azimuthal angle value of the current point is indicative an azimuthal angle of the current point based on a laser used to capture the points of the point cloud.

Predictive geometry coding for point cloud compression

A video coder may code a sign prediction syntax element that indicates whether a sign prediction hypothesis is correct for a transform coefficient. The video coder may code the sign prediction syntax element using a context-based coding process. The video coder may determine a context for coding the sign prediction syntax element based on a position of the transform coefficient in the block of video data. The context may be further based on a coding mode used to code the block.

Context modeling for sign prediction for video coding

Growing community of inventors

San Diego, CA, United States of America

Marta Karczewicz