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

Feasibility of online referencing, realtime performance evaluation

Open
#37 0 comments 2 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
6.3k
Forks
702
PR merge metrics
No merged PRs in 30d

Description

Thank you team for the great job.
I've experienced the source code with video input.
So far, I've seen that the model doesn't produce point clouds while the camera trajectory keeps being displayed.
What should I configure for a better result? Most of the cases I test are indoor scenes.
Second, is it possible to reference input with streaming and can model process and output in real-time?
I see the project page showing SLAM application. How can I experience that? Or it would be great if you could give me some guidelines
Thank you so much!

Image

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.