Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kang, Taeho, Lee, Youngki
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2402.18330
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911785749053440
author Kang, Taeho
Lee, Youngki
author_facet Kang, Taeho
Lee, Youngki
contents We present EgoTAP, a heatmap-to-3D pose lifting method for highly accurate stereo egocentric 3D pose estimation. Severe self-occlusion and out-of-view limbs in egocentric camera views make accurate pose estimation a challenging problem. To address the challenge, prior methods employ joint heatmaps-probabilistic 2D representations of the body pose, but heatmap-to-3D pose conversion still remains an inaccurate process. We propose a novel heatmap-to-3D lifting method composed of the Grid ViT Encoder and the Propagation Network. The Grid ViT Encoder summarizes joint heatmaps into effective feature embedding using self-attention. Then, the Propagation Network estimates the 3D pose by utilizing skeletal information to better estimate the position of obscure joints. Our method significantly outperforms the previous state-of-the-art qualitatively and quantitatively demonstrated by a 23.9\% reduction of error in an MPJPE metric. Our source code is available in GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18330
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Attention-Propagation Network for Egocentric Heatmap to 3D Pose Lifting
Kang, Taeho
Lee, Youngki
Computer Vision and Pattern Recognition
We present EgoTAP, a heatmap-to-3D pose lifting method for highly accurate stereo egocentric 3D pose estimation. Severe self-occlusion and out-of-view limbs in egocentric camera views make accurate pose estimation a challenging problem. To address the challenge, prior methods employ joint heatmaps-probabilistic 2D representations of the body pose, but heatmap-to-3D pose conversion still remains an inaccurate process. We propose a novel heatmap-to-3D lifting method composed of the Grid ViT Encoder and the Propagation Network. The Grid ViT Encoder summarizes joint heatmaps into effective feature embedding using self-attention. Then, the Propagation Network estimates the 3D pose by utilizing skeletal information to better estimate the position of obscure joints. Our method significantly outperforms the previous state-of-the-art qualitatively and quantitatively demonstrated by a 23.9\% reduction of error in an MPJPE metric. Our source code is available in GitHub.
title Attention-Propagation Network for Egocentric Heatmap to 3D Pose Lifting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.18330