EUVIMEDEUVIMED entdecken
Crossref

RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion

Zhiqiang Yan, Xiang Li, Le Hui, Zhenyu Zhang, Jun Li, Jian Yang

International Journal of Computer Vision · 2025-09 · 133 (9) · 6051-6073

DOI: 10.1007/s11263-025-02470-y ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 23.05.2025. Verfasst von Zhiqiang Yan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 108 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Young Scientists Fund of the National Natural Science Foundation of China, Tianjin Key Laboratory of Visual Computing and Intelligent Perception (VCIP), and the Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Depth completion aims to recover dense depth maps from sparse ones, where color images are often used to facilitate this task. Recent depth methods primarily focus on image guided learning frameworks. However, blurry guidance in the image and unclear structure in the depth still impede their performance. To tackle these challenges, we explore a repetitive design in our image guided network to gradually and sufficiently recover depth values. Specifically, the repetition is embodied in both the image guidance branch and depth generation branch. In the former branch, we design a dense repetitive hourglass network (DRHN) to extract discriminative image features of complex environments, which can provide powerful contextual instruction for depth prediction. In the latter branch, we present a repetitive guidance (RG) module based on dynamic convolution, in which an efficient convolution factorization is proposed to reduce the complexity while modeling high-frequency structures progressively. Furthermore, in the semantic guidance branch, we utilize the well-known large vision model, i.e., segment anything (SAM), to supply RG with semantic prior. In addition, we propose a region-aware spatial propagation network (RASPN) for further depth refinement based on the semantic prior constraint. Finally, we collect a new dataset termed TOFDC for the depth completion task, which is acquired by the time-of-flight (TOF) sensor and the color camera on smartphones. Extensive experiments demonstrate that our method achieves state-of-the-art performance on KITTI, NYUv2, Matterport3D, 3D60, VKITTI, and our TOFDC.

Förderung

  • National Natural Science Foundation of China
  • Young Scientists Fund of the National Natural Science Foundation of China
  • Tianjin Key Laboratory of Visual Computing and Intelligent Perception (VCIP), and the Fundamental Research Funds for the Central Universities
  • Fundamental Research Funds for the Central Universities
  • ostgraduate Research & Practice Innovation Program of Jiangsu Province

Zitieren

APA

Yan, Z., Li, X., Hui, L., Zhang, Z., Li, J., & Yang, J. (2025). RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion. International Journal of Computer Vision, 133(9), 6051-6073. https://doi.org/10.1007/s11263-025-02470-y

Vancouver

Yan Z, Li X, Hui L, Zhang Z, Li J, Yang J. RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion. International Journal of Computer Vision. 2025;133(9):6051-6073. doi:10.1007/s11263-025-02470-y

BibTeX
@article{Yan2025,
  author = {Yan, Zhiqiang and Li, Xiang and Hui, Le and Zhang, Zhenyu and Li, Jun and Yang, Jian},
  title = {RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion},
  journal = {International Journal of Computer Vision},
  year = {2025},
  volume = {133},
  number = {9},
  pages = {6051--6073},
  doi = {10.1007/s11263-025-02470-y}
}
Kostenlos starten →