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

Support for long sequences and intuition on how to use the predicted poses and point cloud instead of Colmap in 3dgs

Open
#67 7 comments 3 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
6.3k
Forks
702
PR merge metrics
No merged PRs in 30d

Description

Image

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by inspecting the project entry points for predicted poses and point-cloud output, then compare how those outputs would be used in a 3DGS workflow instead of COLMAP. Done should include support for long sequences and clear guidance on using the predicted poses and point cloud.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.