ai4ce/GARF
[ICCV2025] GARF: Learning Generalizable 3D Reassembly for Real-World Fractures
Flow matching-based approach trained on 1.9M synthetic fractures for generalizable 3D fragment pose estimation, with efficient inference via one-step initialization. Integrates PyTorch3D and PyTorch Lightning for training, supports both flow matching and diffusion variants, and provides evaluation on Breaking Bad and custom fracture datasets via HDF5-based data pipeline.
Stars
93
Forks
11
Language
Python
License
GPL-3.0
Category
Last pushed
Feb 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ai4ce/GARF"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jayin92/Skyfall-GS
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...