Salvato in:
Dettagli Bibliografici
Autori principali: Ren, Kaiwen, Hu, Lei, Zhang, Zhiheng, Ye, Yongjing, Xia, Shihong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2502.12535
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915157716762624
author Ren, Kaiwen
Hu, Lei
Zhang, Zhiheng
Ye, Yongjing
Xia, Shihong
author_facet Ren, Kaiwen
Hu, Lei
Zhang, Zhiheng
Ye, Yongjing
Xia, Shihong
contents Vision-based regression tasks, such as hand pose estimation, have achieved higher accuracy and faster convergence through representation learning. However, existing representation learning methods often encounter the following issues: the high semantic level of features extracted from images is inadequate for regressing low-level information, and the extracted features include task-irrelevant information, reducing their compactness and interfering with regression tasks. To address these challenges, we propose TI-Net, a highly versatile visual Network backbone designed to construct a Transformation Isomorphic latent space. Specifically, we employ linear transformations to model geometric transformations in the latent space and ensure that {\rm TI-Net} aligns them with those in the image space. This ensures that the latent features capture compact, low-level information beneficial for pose estimation tasks. We evaluated TI-Net on the hand pose estimation task to demonstrate the network's superiority. On the DexYCB dataset, TI-Net achieved a 10% improvement in the PA-MPJPE metric compared to specialized state-of-the-art (SOTA) hand pose estimation methods. Our code will be released in the future.
format Preprint
id arxiv_https___arxiv_org_abs_2502_12535
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Transformation-Isomorphic Latent Space for Accurate Hand Pose Estimation
Ren, Kaiwen
Hu, Lei
Zhang, Zhiheng
Ye, Yongjing
Xia, Shihong
Computer Vision and Pattern Recognition
Vision-based regression tasks, such as hand pose estimation, have achieved higher accuracy and faster convergence through representation learning. However, existing representation learning methods often encounter the following issues: the high semantic level of features extracted from images is inadequate for regressing low-level information, and the extracted features include task-irrelevant information, reducing their compactness and interfering with regression tasks. To address these challenges, we propose TI-Net, a highly versatile visual Network backbone designed to construct a Transformation Isomorphic latent space. Specifically, we employ linear transformations to model geometric transformations in the latent space and ensure that {\rm TI-Net} aligns them with those in the image space. This ensures that the latent features capture compact, low-level information beneficial for pose estimation tasks. We evaluated TI-Net on the hand pose estimation task to demonstrate the network's superiority. On the DexYCB dataset, TI-Net achieved a 10% improvement in the PA-MPJPE metric compared to specialized state-of-the-art (SOTA) hand pose estimation methods. Our code will be released in the future.
title Learning Transformation-Isomorphic Latent Space for Accurate Hand Pose Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.12535