normal head supervision
Nobody has claimed this yet.
- Dominant language
- JavaScript
- Stars
- 3k
- Forks
- 234
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
Thanks for great work! I saw on normal.md there is "For convenience, we did not collect ground-truth normal maps for training. Instead, we derived surface normals from the depth map and camera intrinsics." May I have you tried direct gt normal map supervision for normal head? which design choice will give you better results?
Thanks!
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 by reading normal.md, especially the section describing normals derived from the depth map and camera intrinsics. Investigate the normal head's training supervision and compare that design with direct ground-truth normal-map supervision; done means documenting which choice performs better and why.
Written by the indexing model from the issue text.
Assessment
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100