Home

Awesome

Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes / 3DCrowdNet

front_figur

News

:muscle: 3DCrowdNet achieves the state-of-the-art accuracy on 3DPW (3D POSES IN THE WILD DATASET)!
:muscle: We improved PA-MPJPE to 51.1mm and MPVPE to 97.6mm using a ResNet 50 backbone!

Introduction

This repo is the official PyTorch implementation of Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes (CVPR 2022).

Installation

We recommend you to use an Anaconda virtual environment. Install PyTorch >=1.6.0 and Python >= 3.7.3. Then, run sh requirements.sh. You should slightly change torchgeometry kernel code following here.

Quick demo

Preparing

Running

Results

:sunny: Refer to the paper's main manuscript and supplementary material for diverse qualitative results!

table table

Directory

Refer to here.

Reproduction

First finish the directory setting. Then, refer to here to train and evaluate 3DCrowdNet.

Reference

@InProceedings{choi2022learning,  
author = {Choi, Hongsuk and Moon, Gyeongsik and Park, JoonKyu and Lee, Kyoung Mu},  
title = {Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes},  
booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)}
year = {2022}  
}  

Related Projects

I2L-MeshNet_RELEASE
3DCrowdNet_RELEASE
TCMR_RELEASE
Hand4Whole_RELEASE
HandOccNet
NeuralAnnot_RELEASE