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

nested vs streaming in ego centric view video

Open
#210 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

Hello authors and users,

First of all, thanks for your great contribution! this is really breakthrough works !!

These days, I'm trying to estimate camera parameters in the egocentric view named "egocom" dataset.

I considered two version, DA3 nested-large and DA3 streaming.

I already checked depth estimation performance on monocular depth estimation version and it seems works well. but I'm not sure whether nested version and streaming version both can estimate sequences of camera parameter well, and which one should I use.

If others use both, could anyone give me an advice?

Thanks for your assistance in advance.

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.