microsoft / microsoft/TRELLIS

Question about the sdf_bias=-1.0/res in cube2mesh.py

Open
#284 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13.7k
Forks
1.3k
PR merge metrics
No merged PRs in 30d

Description

Hi, I have been trying your great job lately, thank you for sharing this code.

In this line of code (https://github.com/microsoft/TRELLIS/blob/main/trellis/representations/mesh/cube2mesh.py#L111), the original SDF value will be added with a sdf_bias=-1.0/res.
During inference, I forced sdf_bias to be set to 0 and the final generated mesh was also good.
So I want to know why we need this sdf_bias?

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 reading trellis/representations/mesh/cube2mesh.py around line 111 and trace how sdf_bias is used during inference. Compare the documented behavior and generated mesh results with sdf_bias set to -1.0/res and 0; the work is done when the rationale and effect of this parameter are clearly documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-graphics
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 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.