Machine learning techniques for video downsampling
US11948271B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 23, 2020 |
| Grant date | Apr 2, 2024 |
| Priority date | — |
| Expiry date | Feb 28, 2042 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N19/82
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
In various embodiments, a training application trains a convolutional neural network to downsample images in a video encoding pipeline. The convolution neural network includes at least two residual blocks and is associated with a downsampling factor. The training application executes the convolutional neural network on a source image to generate a downsampled image. The training application then executes an upsampling algorithm on the downsampled image to generate a reconstructed image having the same resolution as the source image. The training application computes a reconstruction error based on the reconstructed image and the source image. The training application updates at least one parameter of the convolutional neural network based on the reconstruction error to generate a trained convolutional neural network. Advantageously, the trained convolution neural network can be implemented in a video encoding pipeline to mitigate visual quality reductions typically experienced with conventional video encoding pipelines that implement conventional downsampling techniques.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.