microsoft / microsoft/TRELLIS

Feature extraction includes occluded views without visibility checking

Open
#347 1 comment 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

Description

The current implementation in extract_feature.py extracts DINOv2 features from all views and averages them without checking if a 3D point is actually visible in each view. This leads to feature contamination when points are occluded or on back-facing surfaces. Won't this have a significant impact on the VAE's performance? Or are there other processing details I haven't noticed? Looking forward to your response, 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 with extract_feature.py and trace how DINOv2 features are collected and averaged across views. Determine how visibility and back-facing surfaces are represented in the existing 3D processing, then define validation for excluding occluded views and assess the resulting effect on VAE inputs; the issue is complete when this behavior is specified and verified.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-graphics, machine-learning
Issue type
Feature
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.