pytorch / pytorch/vision

Change CPU decoder output frames to use ITU709 colour space

Open
#5,245 0 comments 0 reactions 1 assignee View on GitHub

@bjuncek is already working on this.

Since Jan 25, 2022.

module: video
Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

GPU decoder outputs frame with ITU709 colour space, whereas CPU decoder uses the default colour space. We need to change the CPU decoder frames to use ITU709 colour space to match the GPU decoder output.
For verification, we could use pyav like this:

av_frames = torch.tensor(av_frame.to_rgb(src_colorspace="ITU709").to_ndarray())

and compare the CPU decoded frames against av_frames.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.