microsoft / microsoft/TRELLIS.2
Color difference is large compared to reference image
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 11.3k
- Forks
- 1.4k
- PR merge metrics
- No merged PRs in 30d
Description
Thanks for releasing this great work!
I’ve been testing TRELLIS-2 and noticed that while the geometry is a significant improvement over TRELLIS-1, the color consistency remains an issue. In many cases, the output colors differ noticeably from the reference images. I’m wondering if this is due to inaccuracies in the PBR estimation, specifically regarding the base color (albedo) not being as precise as expected?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No source file, entry point, or test is named. Start by reproducing the color difference with the attached reference images and tracing the PBR estimation, especially base-color (albedo) output; done would require identifying the cause and establishing that the resulting colors match the reference more closely.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-graphics, machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100