GAP-LAB-CUHK-SZ / GAP-LAB-CUHK-SZ/Total3DUnderstanding
Boundary loss different from TMNet?
Open
- Dominant language
- Python
- Stars
- 445
- Forks
- 52
- PR merge metrics
- No merged PRs in 30d
Description
Looking over the code, it seems like the boundary refinement loss is quite different from the loss used in TMNet.
It seems like in Total3DUnderstanding, the boundary loss is simply [amplifying the chamfer distance](https://github.com/yinyunie/Total3DUnderstanding/blob/master/models/loss.py#L139) for points that exist on the boundary. While in TMNet, there is a neighbor based "smoothing" loss.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.