microsoft / microsoft/TRELLIS.2

strange performance

Open
#41 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
11.3k
Forks
1.4k
PR merge metrics
No merged PRs in 30d

Description

Thank you for your excellent work on this project!

However, I noticed some unusual performance from the model during my testing. Below is the test image I used:

Image

I tested it on the Hugging Face demo with the following configuration, which resulted in poor performance:

Image

The back and bottom of the reconstructed mesh appear empty with significant holes and damage. Could this be due to a mistake on my part during the mesh reconstruction process, or is there a special configuration required for handling this type of image?

Thank you.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the result in the Hugging Face demo with the reported test image and configuration. Inspect the mesh reconstruction process and compare the damaged back and bottom surfaces with a successful reconstruction. Done means determining whether the holes come from the configuration or from a model limitation, with reproduction details documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
computer-graphics, 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.