hanbyel0105/Diff-HMR
Official PyTorch Implementation of "Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models", ICCV 2023 CV4Metaverse Workshop
This project helps create realistic 3D human body models from standard 2D images. It takes a single image of a person and generates multiple possible 3D mesh representations of their body, accounting for different plausible poses or shapes. This is useful for researchers and developers working on virtual reality, augmented reality, or animation applications that require detailed human body models.
No commits in the last 6 months.
Use this if you need to reconstruct 3D human body shapes from 2D images and want to explore multiple plausible interpretations rather than a single fixed output.
Not ideal if you need to track human motion in video or require extremely precise, sub-millimeter accurate body measurements for medical or biomechanical analysis.
Stars
27
Forks
—
Language
—
License
MIT
Category
Last pushed
Oct 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/hanbyel0105/Diff-HMR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...