: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!
This repo is the official PyTorch implementation of Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes (CVPR 2022).
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.
${ROOT}/demo/
. ${ROOT}/demo/input
(just unzip the demo_input.zip).${ROOT}/demo/output
directory.J_regressor_extra.npy
from here and place under ${ROOT}/data/
.
python demo.py --gpu 0
. You can change the input image with --img_idx {img number}
.${ROOT}/demo/
.:sunny: Refer to the paper's main manuscript and supplementary material for diverse qualitative results!
Refer to here.
First finish the directory setting. Then, refer to here to train and evaluate 3DCrowdNet.
@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}
}
I2L-MeshNet_RELEASE
3DCrowdNet_RELEASE
TCMR_RELEASE
Hand4Whole_RELEASE
HandOccNet
NeuralAnnot_RELEASE