EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RAFusion: Integrating Residual Attention for Global Context-Aware 6D Pose Estimation

Wenjin Zhao iD, Yi Lai iD, Qixian Zhang iD, Kang An, Hui Zhang

Sensors · 19.07.2026 · 26 (14) · 4571

DOI: 10.3390/s26144571 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.07.2026. Verfasst von Wenjin Zhao und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, China. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

6D object pose estimation from RGB-D data is a core problem in robotic perception. Representative approaches such as DenseFusion fuse per-pixel RGB and depth features, yet they still face challenges under heavy occlusion and in cluttered backgrounds. This paper revisits the DenseFusion architecture from the perspective of feature enhancement and global context modeling and proposes an enhanced network named RAFusion, which strengthens feature representation through two complementary modules. First, Squeeze-and-Excitation (SE) blocks are integrated into the RGB feature extractor to adaptively reweight channel responses, enhancing salient appearance cues while suppressing noise. Second, a RealFormer-based block is introduced before global pooling, applying residual self-attention to the fused RGB-D features for more effective global context modeling. Experiments on the LINEMOD and Occlusion LINEMOD datasets show that RAFusion improves the DenseFusion baseline and achieves competitive performance compared with representative 6D pose estimation methods. Ablation studies and computational analysis further support the effectiveness of the proposed modules.

Schlagwörter

Stichwörter der Autor:innen

6D pose estimationRGB-D perceptionfeature fusionresidual attention

Autor:innen und Institutionen

  • College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, China.
  • School of Computer Science and Technology, Tongji University, Shanghai 201804, China.

ORCID-Profile: Wenjin Zhao, Yi Lai, Qixian Zhang

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhao, W., Lai, Y., Zhang, Q., An, K., & Zhang, H. (2026). RAFusion: Integrating Residual Attention for Global Context-Aware 6D Pose Estimation. Sensors, 26(14), 4571. https://doi.org/10.3390/s26144571

Vancouver

Zhao W, Lai Y, Zhang Q, An K, Zhang H. RAFusion: Integrating Residual Attention for Global Context-Aware 6D Pose Estimation. Sensors. 2026;26(14):4571. doi:10.3390/s26144571

BibTeX
@article{Zhao2026,
  author = {Zhao, Wenjin and Lai, Yi and Zhang, Qixian and An, Kang and Zhang, Hui},
  title = {RAFusion: Integrating Residual Attention for Global Context-Aware 6D Pose Estimation},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {14},
  pages = {4571},
  doi = {10.3390/s26144571}
}
Kostenlos starten →