dptech-corp/Uni-3DAR
Implementation of paper "Uni-3DAR: Unified 3D Generation and Understanding via Autoregression on Compressed Spatial Tokens"
This project helps scientists and researchers in chemistry and materials science by generating and analyzing 3D molecular and crystal structures. It takes chemical formulas or properties as input and outputs detailed 3D atomic arrangements or predictions about their behavior. This is ideal for computational chemists, material scientists, and drug discovery researchers working with complex 3D structures.
145 stars. No commits in the last 6 months.
Use this if you need to generate novel 3D molecular or crystal structures, predict molecular properties, or understand protein-ligand interactions with high efficiency and accuracy.
Not ideal if you are working with non-atomic 3D data like architectural models or geological formations, or if you do not have access to GPU resources for training and inference.
Stars
145
Forks
16
Language
Python
License
MIT
Category
Last pushed
Apr 21, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/dptech-corp/Uni-3DAR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ZiYang-xie/WorldGen
🌍 WorldGen - Generate Any 3D Scene in Seconds
aioz-ai/AIOZ-GDANCE
AIOZ-GDANCE: a large-scale dataset & baseline for music-driven group dance generation. (CVPR 2023)
worldbench/WorldLens
[CVPR 2026] WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World
Kobaayyy/Awesome-CVPR2026-CVPR2025-ICCV2025-CVPR2024-ECCV2024-AIGC
A Collection of Papers and Codes for CVPR2026/CVPR2025/ICCV2025/CVPR2024/ECCV2024 AIGC
nv-tlabs/XCube
[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies