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: over 1 year ago
Linked 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 |