ByteDance-Seed / ByteDance-Seed/SeedVR
Verify evals on Papers with Code
- Dominant language
- Python
- Stars
- 1.4k
- Forks
- 82
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
Niels here from the open-source team at Hugging Face. Congratulations on your work!
I've made the [paper](https://paperswithcode.co/paper/2506.05301) and [23 paper-native evaluations](https://paperswithcode.co/paper/2506.05301#results) available on Papers with Code.
The paper has results on [Video super-resolution](https://paperswithcode.co/tasks/video-super-resolution) and [Video Restoration](https://paperswithcode.co/tasks/video-restoration) task pages.
The SeedVR2-7B result currently ranks first on [YouHQ40](https://paperswithcode.co/benchmark/youhq40?task=video-super-resolution&eval=17190).
The SeedVR2-3B results currently rank third on [SPMCS](https://paperswithcode.co/benchmark/spmcs?task=video-restoration&eval=10513) and [YouHQ40](https://paperswithcode.co/benchmark/youhq40?task=video-super-resolution&eval=17195).
The SeedVR2-7B result currently ranks third on [UDM10](https://paperswithcode.co/benchmark/udm10?task=video-restoration&eval=10516).
Would it be possible to verify these results and let me know if any score, model name, benchmark protocol, or openness metadata should be corrected?
You can also edit the task, methods, project page, and GitHub URL directly from the paper page using your Hugging Face account.
If you'd like to showcase the results in your repository README, you can copy these live leaderboard badges (or use the “Copy PwC badge” button in the Results section):
[](https://paperswithcode.co/api/v1/papers/2506.05301/leaderboard-badge-link?eval=17190)
[](https://paperswithcode.co/api/v1/papers/2506.05301/leaderboard-badge-link?eval=10513)
[](https://paperswithcode.co/api/v1/papers/2506.05301/leaderboard-badge-link?eval=10516)
Kind regards,
Niels
Contributor guide
No contributing guide indexed for this repository
Research direction
Open the linked Papers with Code paper and review its 23 paper-native evaluations, then compare the SeedVR2-7B and SeedVR2-3B entries with the linked YouHQ40, SPMCS, and UDM10 task and benchmark pages. Done means reporting or correcting any score, model name, protocol, or openness metadata discrepancies and confirming the repository link and task listings.
Written by the indexing model from the issue text.
Assessment
- Domain
- documentation
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100