ai4ce/GARF
[ICCV2025] GARF: Learning Generalizable 3D Reassembly for Real-World Fractures
This project helps in precisely reassembling fragmented 3D objects, like broken bones or pottery, back into their original shape. You input 3D scans of the individual fragments, and it outputs the correct spatial arrangement and orientation needed to reconstruct the complete object. This is useful for archaeologists, paleontologists, forensic scientists, or museum conservators working with delicate or complex broken artifacts.
Use this if you need to digitally reconstruct a 3D object from multiple broken pieces and require highly accurate pose alignment without manual trial and error.
Not ideal if your fragments lack distinct features for alignment or if you are working with 2D images rather than 3D scans.
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
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...