ByteDance-Seed / ByteDance-Seed/Depth-Anything-3
the normalization scheme for extrinsic parameters
- Dominant language
- Python
- Stars
- 6.3k
- Forks
- 702
- PR merge metrics
- No merged PRs in 30d
Description
In the paper, the normalization scheme for extrinsic parameters used during training is different from the one used during inference. What considerations motivated this design choice?
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue does not name an implementation file or test. Start by reading the cited paper and comparing the normalization schemes used during training and inference; then inspect the corresponding training and inference paths in the repository if needed. Done means documenting the design considerations that explain the difference.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100