OpenImagingLab / OpenImagingLab/FlashVSR

Unexpected artifacts on REDS video with official FlashVSR inference

Open
#99 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.9k
Forks
152
PR merge metrics
No merged PRs in 30d

Description

Hi, thanks for releasing FlashVSR.

I’m observing noticeable visual artifacts when running the official infer_flashvsr_v1.1_tiny_long_video.py script on a REDS video with bicubic degradation. The input resolution is 320×180, and the output resolution is 1280×640. I attached a few example frames below.

I also observe artifacts with infer_flashvsr_v1.1_full.py, but the attached screenshots here are from the tiny long video script.

Is this expected behavior, or could something be wrong in the inference setup?

Image Image Image Image

Contributor guide

No contributing guide indexed for this repository

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.

Research direction

Start by reproducing the reported artifacts with infer_flashvsr_v1.1_tiny_long_video.py on the REDS video using bicubic degradation, then compare with infer_flashvsr_v1.1_full.py. Check whether the 320×180 input and 1280×640 output reproduce the attached behavior; the issue is done when the cause or expected behavior is established.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.