Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction
To overcome the above issues, we introduce CycleAdapt, which cyclically adapts two networks: a human mesh reconstruction network (HMRNet) and a human motion denoising ...
Tags：Paper and LLMsDenoisingPricing Type
- Pricing Type: Free
- Price Range Start($):
GitHub Link
The GitHub link is https://github.com/hygenie1228/cycleadapt_release
Introduce
This GitHub repository, “CycleAdapt_RELEASE,” presents the official PyTorch implementation of a method for 3D human mesh reconstruction from monocular videos. The method, called Cyclic Test-Time Adaptation, is introduced by Hyeongjin Nam, Daniel Sungho Jung, Yeonguk Oh, and Kyoung Mu Lee, and it was presented at the International Conference on Computer Vision (ICCV) in 2023. The installation instructions involve using an Anaconda virtual environment, installing PyTorch >=1.8.0 and Python >=3.7.0, and running the required dependencies. The repository provides a quick demo, details on running CycleAdapt on custom videos, and instructions to evaluate adapted models. The paper’s reference is provided for further information.
To overcome the above issues, we introduce CycleAdapt, which cyclically adapts two networks: a human mesh reconstruction network (HMRNet) and a human motion denoising network (MDNet), given a test video.
Content
In the asset/yaml/*.yml, you can change datasets and settings to use. To evaluate the adapted models in your experiment folder, run Refer to the paper’s main manuscript and supplementary material for diverse qualitative results.
Related
