ByteDance-Seed / ByteDance-Seed/Depth-Anything-3

About the distance-weights of the surface-normal loss

Open
#227 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
6.3k
Forks
702
PR merge metrics
No merged PRs in 30d

Description

In the distance-weighted surface-normal loss, are the distance weights computed from the predicted point map kept attached to the computation graph, or are they detached?

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.