EFFICIENT WARPING-BASED NEURAL VIDEO CODEC

Organization Name

QUALCOMM Incorporated

Inventor(s)

Ties Jehan Van Rozendaal of Amsterdam (NL)

Hoang Cong Minh Le of Santee CA (US)

Tushar Singhal of San Diego CA (US)

Amir Said of San Diego CA (US)

Krishna Buska of San Diego CA (US)

Guillaume Konrad Sautiere of Amsterdam (NL)

Anjuman Raha of San Diego CA (US)

Auke Joris Wiggers of Amsterdam (NL)

Frank Steven Mayer of San Diego CA (US)

Liang Zhang of San Diego CA (US)

Abhijit Khobare of San Diego CA (US)

Muralidhar Reddy Akula of San Diego CA (US)

EFFICIENT WARPING-BASED NEURAL VIDEO CODEC - A simplified explanation of the abstract

This abstract first appeared for US patent application 18457079 titled 'EFFICIENT WARPING-BASED NEURAL VIDEO CODEC

The abstract describes a computing device that can decode encoded video data, predict motion vectors, and generate current reconstructed video data.

Memory and processors in the computing device
Parallel entropy decoding of video data from a bitstream
Prediction of motion vectors based on decoded data
Decoding of motion vector residuals
Addition of motion vector residuals and motion vectors
Warping of previous video data using motion vectors
Summing predicted video data with residual blocks to generate current reconstructed video data

Potential Applications: - Video streaming services - Video surveillance systems - Video conferencing platforms

Problems Solved: - Efficient video data decoding - Accurate motion vector prediction - Seamless video data reconstruction

Benefits: - Improved video quality - Reduced data transmission bandwidth - Enhanced video processing speed

Commercial Applications: Title: "Enhanced Video Decoding Technology for Improved Quality" This technology can be used in various commercial applications such as video streaming services, video surveillance systems, and video conferencing platforms. It can improve video quality, reduce bandwidth requirements, and enhance video processing speed, leading to a better user experience and cost savings for businesses.

Questions about the technology: 1. How does this technology improve video quality compared to traditional methods? This technology enhances video quality by accurately predicting motion vectors and efficiently reconstructing video data, resulting in clearer and smoother playback.

2. What are the potential cost savings for businesses implementing this video decoding technology? Businesses can save costs on data transmission bandwidth and processing resources by using this technology, leading to more efficient video streaming and storage solutions.

Original Abstract Submitted

An example computing device may include memory and one or more processors. The one or more processors may be configured to parallel entropy decode encoded video data from a received bitstream to generate entropy decoded data. The one or more processors may be configured to predict a motion vector based on the entropy decoded data. The one or more processors may be configured to decode a motion vector residual from the entropy decoded data. The one or more processors may be configured to add the motion vector residual and motion vector. The one or more processors may be configured to warp previous reconstructed video data with an overlapped block-based warp function using the motion vector to generate predicted current video data. The one or more processors may be configured to sum the predicted current video data with a residual block to generate current reconstructed video data.