Skip to content

Latest commit

 

History

History
86 lines (64 loc) · 2.79 KB

README.md

File metadata and controls

86 lines (64 loc) · 2.79 KB
Raw

3D Clothed Human Reconstruction in the Wild (ClothWild codes)

3D Clothed Human Reconstruction in the Wild,
Gyeongsik Moon*, Hyeongjin Nam*, Takaaki Shiratori, Kyoung Mu Lee (* equal contribution)
European Conference on Computer Vision (ECCV), 2022

Installation

  • We recommend you to use an Anaconda virtual environment. Install PyTorch >=1.8.0 and Python >= 3.7.0.
  • Install Pytorch3d following here depending on your environment.
  • Then, run sh requirements.sh. You should slightly change torchgeometry kernel code following here.

Quick demo

  • Download the pre-trained weight from here and place it in demo folder.
  • Prepare base_data folder following below Directory part.
  • Prepare input.png and edit its bbox of demo/demo.py.
  • Prepare SMPL parameter, as pose2pose_result.json. You can get the SMPL parameter by running the off-the-shelf method [code].
  • Run python demo.py --gpu 0.

Directory

Refer to here.

Running ClothWild

Train

In the main/config.py, you can change datasets to use.

cd ${ROOT}/main
python train.py --gpu 0

Test

Place trained model at the output/model_dump and follow below.

To evaluate CD (Chamfer Distance) on 3DPW, run

cd ${ROOT}/main
python test.py --gpu 0 --test_epoch 7 --type cd

To evaluate BCC (Body-Cloth Correspondence) on MSCOCO, run

cd ${ROOT}/main
python test.py --gpu 0 --test_epoch 7 --type bcc

You can download the checkpoint trained on MSCOCO+DeepFashion2 from here.

Result

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

Chamfer Distance (CD)

Body-Cloth Correspondence (BCC)

Reference

@InProceedings{Moon_2022_ECCV_ClothWild,  
author = {Moon, Gyeongsik and Nam, Hyeongjin and Shiratori, Takaaki and Lee, Kyoung Mu},  
title = {3D Clothed Human Reconstruction in the Wild},  
booktitle = {European Conference on Computer Vision (ECCV)},  
year = {2022}  
}