GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Zinqin, Wang, Gu, Zhang, Chenyangguang, Zhang, Ruida, Li, Xiu, Ji, Xiangyang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912283771273216
author Huang, Zinqin
Wang, Gu
Zhang, Chenyangguang
Zhang, Ruida
Li, Xiu
Ji, Xiangyang
author_facet Huang, Zinqin
Wang, Gu
Zhang, Chenyangguang
Zhang, Ruida
Li, Xiu
Ji, Xiangyang
contents Recent advances in RGBD-based category-level object pose estimation have been limited by their reliance on precise depth information, restricting their broader applicability. In response, RGB-based methods have been developed. Among these methods, geometry-guided pose regression that originated from instance-level tasks has demonstrated strong performance. However, we argue that the NOCS map is an inadequate intermediate representation for geometry-guided pose regression method, as its many-to-one correspondence with category-level pose introduces redundant instance-specific information, resulting in suboptimal results. This paper identifies the intra-class variation problem inherent in pose regression based solely on the NOCS map and proposes the Intra-class Variation-Free Consensus (IVFC) map, a novel coordinate representation generated from the category-level consensus model. By leveraging the complementary strengths of the NOCS map and the IVFC map, we introduce GIVEPose, a framework that implements Gradual Intra-class Variation Elimination for category-level object pose estimation. Extensive evaluations on both synthetic and real-world datasets demonstrate that GIVEPose significantly outperforms existing state-of-the-art RGB-based approaches, achieving substantial improvements in category-level object pose estimation. Our code is available at https://github.com/ziqin-h/GIVEPose.
format Preprint
id arxiv_https___arxiv_org_abs_2503_15110
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation
Huang, Zinqin
Wang, Gu
Zhang, Chenyangguang
Zhang, Ruida
Li, Xiu
Ji, Xiangyang
Computer Vision and Pattern Recognition
Recent advances in RGBD-based category-level object pose estimation have been limited by their reliance on precise depth information, restricting their broader applicability. In response, RGB-based methods have been developed. Among these methods, geometry-guided pose regression that originated from instance-level tasks has demonstrated strong performance. However, we argue that the NOCS map is an inadequate intermediate representation for geometry-guided pose regression method, as its many-to-one correspondence with category-level pose introduces redundant instance-specific information, resulting in suboptimal results. This paper identifies the intra-class variation problem inherent in pose regression based solely on the NOCS map and proposes the Intra-class Variation-Free Consensus (IVFC) map, a novel coordinate representation generated from the category-level consensus model. By leveraging the complementary strengths of the NOCS map and the IVFC map, we introduce GIVEPose, a framework that implements Gradual Intra-class Variation Elimination for category-level object pose estimation. Extensive evaluations on both synthetic and real-world datasets demonstrate that GIVEPose significantly outperforms existing state-of-the-art RGB-based approaches, achieving substantial improvements in category-level object pose estimation. Our code is available at https://github.com/ziqin-h/GIVEPose.
title GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.15110