EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ACT‐Agent: Affinity‐Cross Transformer for Point Cloud Registration via Reinforcement Learning

Fengguang Xiong, Haixin Gong, Qiao Ma, Yingbo Jia, Ruize Guo, Yu Cao, Ligang He, Liqun Kuang, Xie Han

IET Image Processing · 2026-01 · 20 (1)

DOI: 10.1049/ipr2.70283 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Image Processing, online erschienen am 09.01.2026. Verfasst von Fengguang Xiong und 8 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Point cloud registration, a core task in 3D computer vision for aligning two point clouds via rotation and translation, underpins critical applications like robotic navigation and 3D reconstruction. Classical methods (e.g., Iterative Closest Point) easily converge to local minima under poor initial alignment. Deep learning–based approaches, while efficient, suffer from high annotation costs for large‐scale data. Existing reinforcement learning (RL)‐based methods rely on simple PointNet feature extractors, which are insensitive to local geometric details and thus yield suboptimal registration precision. To address these challenges, we propose ACT‐Agent: Affinity‐Cross Transformer for point cloud registration via reinforcement learning, a novel method that formulates point cloud registration as an RL Markov decision process for iterative optimisation. We leverage Pointnet and Affinity‐Cross Transformer to extract and enhance expressive salient features and assign adaptive weights to channels based on their relative importance. We use RL to autonomously learn from feedback in the environment, freeing ourselves from dependence on data annotation. Experimental results on ModelNet40 (synthetic data) and ScanObjectNN (real‐world data) demonstrate that our proposed ACT‐Agent achieves higher accuracy, efficiency, and generalisation ability than the state‐of‐the‐art methods of point cloud registration.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Xiong, F., Gong, H., Ma, Q., Jia, Y., Guo, R., Cao, Y., He, L., Kuang, L., & Han, X. (2026). ACT‐Agent: Affinity‐Cross Transformer for Point Cloud Registration via Reinforcement Learning. IET Image Processing, 20(1). https://doi.org/10.1049/ipr2.70283

Vancouver

Xiong F, Gong H, Ma Q, Jia Y, Guo R, Cao Y, et al. ACT‐Agent: Affinity‐Cross Transformer for Point Cloud Registration via Reinforcement Learning. IET Image Processing. 2026;20(1). doi:10.1049/ipr2.70283

BibTeX
@article{Xiong2026,
  author = {Xiong, Fengguang and Gong, Haixin and Ma, Qiao and Jia, Yingbo and Guo, Ruize and Cao, Yu and He, Ligang and Kuang, Liqun and Han, Xie},
  title = {ACT‐Agent: Affinity‐Cross Transformer for Point Cloud Registration via Reinforcement Learning},
  journal = {IET Image Processing},
  year = {2026},
  volume = {20},
  number = {1},
  doi = {10.1049/ipr2.70283}
}
Kostenlos starten →