Home

Awesome

Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction (CycleAdapt codes)

Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction,
Hyeongjin Nam, Daniel Sungho Jung, Yeonguk Oh, Kyoung Mu Lee,
International Conference on Computer Vision (ICCV), 2023

<p align="center"> <img src="asset/front_figure.png" style="width:65%"> </p> <p align="center"> <img src="asset/qualitative_result.gif" style="width:65%"> </p>

Installation

Quick demo

Directory

Refer to here.

Running CycleAdapt

In the asset/yaml/*.yml, you can change datasets and settings to use.

Run

python main/adapt.py  --gpu 0 --cfg asset/yaml/3dpw.yml

To evaluate the adapted models in your experiment folder, run

python main/test.py --gpu 0 --cfg asset/yaml/3dpw.yml --exp-dir {exp_path}

Result

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

<p align="center"> <img src="asset/quantitative_result.png" style="width:65%"> </p>

Reference

@InProceedings{Nam_2023_ICCV_CycleAdapt,  
author = {Nam, Hyeongjin and Jung, Daniel Sungho and Oh, Yeonguk and Lee, Kyoung Mu},  
title = {Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction},  
booktitle = {International Conference on Computer Vision (ICCV)},  
year = {2023}  
}