DaNet-DensePose2SMPL
Human reconstruction tool
This repository provides software tools and pre-trained models for estimating 3D human shape and pose from dense body parts
[TPAMI 2020] Learning 3D Human Shape and Pose from Dense Body Parts
233 stars
9 watching
32 forks
Language: Python
last commit: about 3 years agoLinked from 1 awesome list
3d-human-reconstruction3d-human-shape-and-pose-estimationdensepose-to-smplhuman-mesh-recoverysmpl
Related projects:
| Repository | Description | Stars |
|---|---|---|
| Reconstructs human 3D models from monocular images using a feedback loop to improve pose and shape estimation | 600 | |
| An implementation of CloudWalk's DenseBody paper using PyTorch | 411 | |
| An implementation of an expressive human pose and shape estimation system using deep learning techniques | 1,027 | |
| An open-source software project that enables the recovery of full-body 3D human models from monocular images. | 230 | |
| Develops a method to reconstruct 3D wireframe models from a single image using deep learning | 70 | |
| Provides pseudo-GT 3D human pose data and pre-trained models for training 3D pose estimation algorithms | 379 | |
| An implementation of human instance segmentation based on pose estimation | 529 | |
| A PyTorch implementation of a 3D human pose estimation algorithm using weak supervision. | 613 | |
| A PyTorch implementation of a deep learning model for 3D multi-person pose estimation from a single RGB image | 825 | |
| A high-performance pose estimation library for building custom applications. | 1,257 | |
| Provides a modular framework and tools for working with 3D human parametric models in computer vision and graphics | 1,253 | |
| A large-scale benchmark and dataset for whole-body pose estimation in images | 770 | |
| Detects humans and estimates their poses in images using a machine learning model based on OpenPose | 65 | |
| A system for generating 3D human models from 2D image collections using deep learning | 590 | |
| A lightweight human body posture key point model using computer vision and deep learning techniques. | 302 |