3DTopia / 3DTopia/GenDoP

depth does not work in Text & RGBD-to-Trajectory generation?

Open
#5 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
129
Forks
8
PR merge metrics
No merged PRs in 30d

Description

Hi, @kszpxxzmc, in the Text & RGBD-to-Trajectory generation (official example), the depth value does not affect the final generated trajectory. For example, multiply the value of depth by 10, but it seems that the length and scale of the generated trajectory does not change significantly. I'm not sure if I got any mistake, here is my running log:[log.txt](https://github.com/user-attachments/files/23251821/log.txt)

Contributor guide

No contributing guide indexed for this repository

Research direction

Reproduce the Text & RGBD-to-Trajectory generation official example using the attached log.txt, first comparing the normal depth value with one multiplied by 10. Trace where depth enters trajectory generation and determine whether the resulting trajectory length and scale should change; done means the behavior is explained and, if it is a bug, covered by a reproducible fix and test.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.