Turn any human pose estimation using images to use video for better performance with simple PoseBERT
Turn any human pose estimation using images to use video for better performance with simple PoseBERT
PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling
arXiv paper abstract https://arxiv.org/abs/2208.10211v1
arXiv PDF paper https://arxiv.org/pdf/2208.10211v1.pdf
GitHub https://github.com/naver/posebert
Training state-of-the-art models for human pose estimation in videos requires datasets with annotations that are really hard and expensive to obtain.
… introduce PoseBERT, a transformer module that is fully trained on 3D Motion Capture (MoCap) data via masked modeling.
… can be plugged on top of any image-based model to transform it in a video-based model leveraging temporal information.
… showcase variants of PoseBERT with different inputs varying from 3D skeleton keypoints to rotations of a 3D parametric model for either the full body (SMPL) or just the hands (MANO).
… PoseBERT … task agnostic … can be applied to several tasks such as pose refinement, future pose prediction or motion completion without finetuning.
… adding PoseBERT on top of various state-of-the-art pose estimation methods consistently improves their performances, while its low computational cost allows us to use it in a real-time demo for smoothly animating a robotic hand via a webcam …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
