EUVIMEDEUVIMED entdecken
Crossref

Camera-Based 3D Semantic Scene Completion With Sparse Guidance Network

Jianbiao Mei, Yu Yang, Mengmeng Wang, Junyu Zhu, Jongwon Ra, Yukai Ma, Laijian Li, Yong Liu

IEEE Transactions on Image Processing · 2024 · 33 · 5468-5481

DOI: 10.1109/tip.2024.3461989 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Jianbiao Mei und 7 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Autonomous Intelligent Unmanned Systems.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic scene completion (SSC) aims to predict the semantic occupancy of each voxel in the entire 3D scene from limited observations, which is an emerging and critical task for autonomous driving. Recently, many studies have turned to camera-based SSC solutions due to the richer visual cues and cost-effectiveness of cameras. However, existing methods usually rely on sophisticated and heavy 3D models to process the lifted 3D features directly, which are not discriminative enough for clear segmentation boundaries. In this paper, we adopt the dense-sparse-dense design and propose a one-stage camera-based SSC framework, termed SGN, to propagate semantics from the semantic-aware seed voxels to the whole scene based on spatial geometry cues. Firstly, to exploit depth-aware context and dynamically select sparse seed voxels, we redesign the sparse voxel proposal network to process points generated by depth prediction directly with the coarse-to-fine paradigm. Furthermore, by designing hybrid guidance (sparse semantic and geometry guidance) and effective voxel aggregation for spatial geometry cues, we enhance the feature separation between different categories and expedite the convergence of semantic propagation. Finally, we devise the multi-scale semantic propagation module for flexible receptive fields while reducing the computation resources. Extensive experimental results on the SemanticKITTI and SSCBench-KITTI-360 datasets demonstrate the superiority of our SGN over existing state-of-the-art methods. And even our lightweight version SGN-L achieves notable scores of 14.80% mIoU and 45.45% IoU on SeamnticKITTI validation with only 12.5 M parameters and 7.16 G training memory. Code is available at https://github.com/Jieqianyu/SGN.

Förderung

  • National Natural Science Foundation of China
  • Autonomous Intelligent Unmanned Systems

Zitieren

APA

Mei, J., Yang, Y., Wang, M., Zhu, J., Ra, J., Ma, Y., Li, L., & Liu, Y. (2024). Camera-Based 3D Semantic Scene Completion With Sparse Guidance Network. IEEE Transactions on Image Processing, 33, 5468-5481. https://doi.org/10.1109/tip.2024.3461989

Vancouver

Mei J, Yang Y, Wang M, Zhu J, Ra J, Ma Y, et al. Camera-Based 3D Semantic Scene Completion With Sparse Guidance Network. IEEE Transactions on Image Processing. 2024;33:5468-5481. doi:10.1109/tip.2024.3461989

BibTeX
@article{Mei2024,
  author = {Mei, Jianbiao and Yang, Yu and Wang, Mengmeng and Zhu, Junyu and Ra, Jongwon and Ma, Yukai and Li, Laijian and Liu, Yong},
  title = {Camera-Based 3D Semantic Scene Completion With Sparse Guidance Network},
  journal = {IEEE Transactions on Image Processing},
  year = {2024},
  volume = {33},
  pages = {5468--5481},
  doi = {10.1109/tip.2024.3461989}
}
Kostenlos starten →