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

Why is the camera encoder/decoder model block invoked to re-predict the intrinsic and extrinsic parameters when specifying them?

Open
#148 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 code:
(1) Why is the camera encoder/decoder model block invoked to re-predict the intrinsic and extrinsic parameters when specifying them?
(2) Didn’t the paper recover the camera intrinsic and extrinsic parameters using ray information and point out that directly predicting the camera intrinsic and extrinsic parameters fails to satisfy the orthogonality constraint?

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.