Machine-learned in-loop predictor for video compression
US11570465B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 25, 2021 |
| Grant date | Jan 31, 2023 |
| Priority date | — |
| Expiry date | Aug 25, 2041 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N19/65
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
A compression system trains a compression model for an encoder and decoder. In one embodiment, the compression model includes a machine-learned in-loop flow predictor that generates a flow prediction from previously reconstructed frames. The machine-learned flow predictor is coupled to receive a set of previously reconstructed frames and output a flow prediction for a target frame that is an estimation of the flow for the target frame. In particular, since the flow prediction can be generated by the decoder using the set of previously reconstructed frames, the encoder may transmit a flow delta that indicates a difference between the flow prediction and the actual flow for the target frame, instead of transmitting the flow itself. In this manner, the encoder can transmit a significantly smaller number of bits to the receiver, improving computational efficiency.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.