💪 3DCrowdNet achieves the state-of-the-art accuracy on 3DPW (3D POSES IN THE WILD DATASET)!
💪 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.

• Download the pre-trained 3DCrowdNet checkpoint from here and place it under ${ROOT}/demo/.
• Download demo inputs from here and place them under ${ROOT}/demo/input (just unzip the demo_input.zip).
• Make ${ROOT}/demo/output directory.
• Get SMPL layers and VPoser according to this.
• Download J_regressor_extra.npy from here and place under ${ROOT}/data/.

• Run python demo.py --gpu 0. You can change the input image with --img_idx {img number}.
• A mesh obj, a rendered mesh image, and an input 2d pose are saved under ${ROOT}/demo/.
• The demo images and 2D poses are from CrowdPose and HigherHRNet respectively.
• The depth order is not estimated. You can manually change it.

☀️ 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