CT3D++: Improving 3D Object Detection with Keypoint-Induced Channel-wise Transformer
International Journal of Computer Vision · 2025-07 · 133 (7) · 4817-4836
DOI: 10.1007/s11263-025-02404-8 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 20.03.2025. Verfasst von Hualian Sheng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 80 Literaturangaben.
Abstract (Originalsprache)
The field of 3D object detection from point clouds is rapidly advancing in computer vision, aiming to accurately and efficiently detect and localize objects in three-dimensional space. Current 3D detectors commonly fall short in terms of flexibility and scalability, with ample room for advancements in performance. In this paper, our objective is to address these limitations by introducing two frameworks for 3D object detection. Firstly, we propose CT3D, which sequentially performs raw-point-based embedding, a standard Transformer encoder, and a channel-wise decoder for point features within each proposal. Secondly, we present an enhanced network called CT3D++, which incorporates geometric and semantic fusion-based embedding to extract more valuable and comprehensive proposal-aware information. Additionally, CT3D++ utilizes a point-to-key bidirectional encoder for more efficient feature encoding with reduced computational cost. By replacing the corresponding components of CT3D with these novel modules, CT3D++ achieves state-of-the-art performance on both the KITTI dataset and the large-scale Waymo Open Dataset. The source code for our frameworks will be made accessible at https://github.com/hlsheng1/CT3Dplusplus.
Zitieren
APA
Sheng, H., Cai, S., Zhao, N., Deng, B., Liang, Q., Zhao, M., & Ye, J. (2025). CT3D++: Improving 3D Object Detection with Keypoint-Induced Channel-wise Transformer. International Journal of Computer Vision, 133(7), 4817-4836. https://doi.org/10.1007/s11263-025-02404-8
Vancouver
Sheng H, Cai S, Zhao N, Deng B, Liang Q, Zhao M, et al. CT3D++: Improving 3D Object Detection with Keypoint-Induced Channel-wise Transformer. International Journal of Computer Vision. 2025;133(7):4817-4836. doi:10.1007/s11263-025-02404-8
BibTeX
@article{Sheng2025,
author = {Sheng, Hualian and Cai, Sijia and Zhao, Na and Deng, Bing and Liang, Qiao and Zhao, Min-Jian and Ye, Jieping},
title = {CT3D++: Improving 3D Object Detection with Keypoint-Induced Channel-wise Transformer},
journal = {International Journal of Computer Vision},
year = {2025},
volume = {133},
number = {7},
pages = {4817--4836},
doi = {10.1007/s11263-025-02404-8}
}
EUVIMED