18286574. VIDEO INTER/INTRA COMPRESSION USING MIXTURE OF EXPERTS simplified abstract (Google LLC)
Contents
VIDEO INTER/INTRA COMPRESSION USING MIXTURE OF EXPERTS
Organization Name
Inventor(s)
David Charles Minnen of Mountain View CA (US)
Sung Jin Hwang of Mountain View CA (US)
Elliott Michael Karpilovsky of Santa Clara CA (US)
Debargha Mukherjee of Cupertino CA (US)
VIDEO INTER/INTRA COMPRESSION USING MIXTURE OF EXPERTS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18286574 titled 'VIDEO INTER/INTRA COMPRESSION USING MIXTURE OF EXPERTS
Simplified Explanation: The patent application describes methods, systems, and apparatus for compressing and decompressing video data using a combination of machine learning models. Frames in a video are divided into blocks, and predictions for each block are made based on borders of neighboring blocks in sequential sets of frames.
- Ensemble of machine learning models used for compression and decompression of video data
- Dividing video frames into blocks for processing
- Predictions for blocks based on borders of neighboring blocks in sequential sets of frames
Potential Applications: This technology can be applied in video streaming services, video editing software, surveillance systems, and virtual reality applications.
Problems Solved: This technology addresses the challenge of efficiently compressing and decompressing video data while maintaining high quality and reducing file sizes.
Benefits: The benefits of this technology include improved video compression efficiency, reduced bandwidth requirements for streaming, and enhanced video quality.
Commercial Applications: Optimizing video streaming services, enhancing video editing software, improving surveillance systems, and enhancing virtual reality experiences are potential commercial applications of this technology.
Prior Art: Prior research in video compression algorithms and machine learning models can provide insights into the development of this technology.
Frequently Updated Research: Stay updated on advancements in machine learning models for video compression and decompression to enhance the efficiency and effectiveness of this technology.
Questions about Video Compression using Machine Learning: 1. How does this technology improve video compression compared to traditional methods? 2. What are the key factors influencing the accuracy of predictions for video data compression using machine learning models?
Original Abstract Submitted
Methods, systems, and apparatus, including computer programs, for compression and decompression of video data using an ensemble of machine learning models. Methods can include defining for each frame in a video, a plurality of blocks in the frame. Methods can further include processing the frames of video in sequential sets, wherein each sequential set is at least a current frame () of video and a prior frame () of video in the ordered sequence. Each respective prediction of a block in the frame of the video includes providing, as input to a prediction model a first and the second border () of a current block () of the current frame, a first and a second border () for a respective current block () of the prior frame and the respective current block () of the prior frame.
