desaixie/zeroverse

Official code for NeurIPS 2024 paper LRM-Zero: Training Large Reconstruction Models with Synthesized Data

37
/ 100
Emerging

Zeroverse helps computer vision researchers and 3D content creators generate vast datasets of unique 3D objects with varied shapes and materials. It takes simple commands to define object parameters and outputs diverse 3D models (in .obj, .mtl, .glb formats) and rendered images for training large reconstruction models. This tool is ideal for those needing large-scale, synthetically generated 3D data.

153 stars. No commits in the last 6 months.

Use this if you need to create a large dataset of procedurally generated 3D objects and their rendered views for machine learning research or 3D asset development.

Not ideal if you need to generate highly realistic, photogrammetry-based 3D models of real-world objects or require specific, artist-designed models.

3D-model-generation synthetic-data-generation computer-vision-research 3D-asset-creation machine-learning-dataset
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

153

Forks

11

Language

Python

License

Last pushed

Oct 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/desaixie/zeroverse"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.