wrk226/DiffProxy
Official repo of "DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies“
DiffProxy helps researchers and engineers accurately reconstruct 3D human body shapes and poses from multiple camera angles. It takes several 2D images of a person from different viewpoints and generates a precise 3D model of their body. This is useful for anyone working with human motion analysis or virtual character creation.
Use this if you need to create accurate 3D digital models of human bodies from video footage captured by multiple cameras.
Not ideal if you only have a single image of a person or are working with non-human subjects.
Stars
8
Forks
—
Language
—
License
MIT
Category
Last pushed
Jan 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/wrk226/DiffProxy"
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...