microsoft / microsoft/TRELLIS

How to encode existing 3D models (mesh or gaussian splat)?

Open
#17 1 comment 9 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

I see that the only usage documentation provided by the readme uses an image as the input. However, this VAE architecture should be able to accept a diverse set of inputs, since the inputs to the VAE were voxelized features from a 3D model during training stage.

I want to know how we can encode existing 3D models (mesh or gaussian splat) to the embedding space using the trellis library.

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 with the README's image-input example and review the TRELLIS library's VAE and voxelized-feature workflow. Determine whether existing mesh or Gaussian-splat inputs are supported, then document a reproducible encoding path or clearly identify the missing capability. No specific files or tests are named in the issue.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-graphics, machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.