Residual Regression Pose Estimation Network Based on Dynamic Reference Points
IEEE Sensors Journal · 15.05.2026 · 26 (10) · 15716-15727
DOI: 10.1109/jsen.2026.3678960 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 15.05.2026. Verfasst von Chao Sun und 4 weiteren Autor:innen. Gefördert von: National Key Research and Development Program of China, Teaching and Research Project of Hubei Provincial Department of Education, Industry-University-Research Project of Wuhan Municipal Education Bureau.
Abstract (Originalsprache)
To address challenges such as specular reflections on metal surfaces, limited texture, and severe occlusion in industrial scenarios, this article proposes a residual regression pose estimation network based on dynamic reference points, which achieves robust six-degree-of-freedom (6DoF) pose prediction of workpieces from a single RGB-D image. Our method first performs preprocessing, including cropping and normalization of the RGB-D image according to object detection results, to improve input data quality. A dynamic reference point allocation strategy, designed based on object size and curvature information, is combined with a residual representation of 3-D object coordinates, effectively reducing the output space and enhancing attention to key geometric regions. The network introduces a bidirectional fusion module that integrates RGB and depth information to extract and combine appearance and geometric features in a multiscale manner. Finally, by establishing dense correspondences, the network jointly predicts the 6DoF object pose. On the LM-Occluded dataset, the proposed method achieves an average improvement of 4.8% in the ADD-S 0.1d metric over existing baselines, achieves a 7% average improvement on our custom metal workpiece dataset, and maintains high robustness under complex occlusion conditions, demonstrating the effectiveness of our approach.
Förderung
- National Key Research and Development Program of China
- Teaching and Research Project of Hubei Provincial Department of Education
- Industry-University-Research Project of Wuhan Municipal Education Bureau
Zitieren
APA
Sun, C., Ye, Z., Li, X., Qin, C., & Ding, J. (2026). Residual Regression Pose Estimation Network Based on Dynamic Reference Points. IEEE Sensors Journal, 26(10), 15716-15727. https://doi.org/10.1109/jsen.2026.3678960
Vancouver
Sun C, Ye Z, Li X, Qin C, Ding J. Residual Regression Pose Estimation Network Based on Dynamic Reference Points. IEEE Sensors Journal. 2026;26(10):15716-15727. doi:10.1109/jsen.2026.3678960
BibTeX
@article{Sun2026,
author = {Sun, Chao and Ye, Zian and Li, Xiahui and Qin, Chengji and Ding, Jianjun},
title = {Residual Regression Pose Estimation Network Based on Dynamic Reference Points},
journal = {IEEE Sensors Journal},
year = {2026},
volume = {26},
number = {10},
pages = {15716--15727},
doi = {10.1109/jsen.2026.3678960}
}
EUVIMED