OpenImagingLab / OpenImagingLab/FlashVSR
在金属材质上产生了非常差的结果
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.9k
- Forks
- 152
- PR merge metrics
- No merged PRs in 30d
Description
大佬，flashvsr项目在大部分输入上都能达到非常好的效果，并且速度上的优势非常大，但最近测试出一类case非常容易产生严重的像素抖动问题，尤其在金属材质的像素上
输入：
https://github.com/user-attachments/assets/76950780-3fa7-453c-9b22-120c84cac7f2
输出：
https://github.com/user-attachments/assets/24c5cede-24d4-49ff-810a-7dbe9071c218
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the input and output attachments in issue #104 and reproduce the metallic-material case using the documented FlashVSR workflow. Trace the video super-resolution inference path to identify the source of the pixel jitter; done means the case produces stable output without the reported severe artifacts.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100