eric-zqwang/puzzlefusion-plusplus
Code for paper "PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify" [ICLR 2025]
This project helps researchers and engineers working with fragmented 3D objects to automatically reassemble them. You provide a collection of 3D fragments from a broken object, and the system outputs the reconstructed 3D object. This is ideal for those involved in fields like archaeology, forensics, or industrial design where physical objects need digital reconstruction.
No commits in the last 6 months.
Use this if you need to digitally reconstruct a complete 3D object from a set of fractured or broken 3D pieces.
Not ideal if your fragments are not from a single broken object, or if you require human-guided assembly rather than an automated solution.
Stars
67
Forks
9
Language
Python
License
—
Category
Last pushed
Mar 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/eric-zqwang/puzzlefusion-plusplus"
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...