EUVIMEDEUVIMED entdecken
Crossref

Refine3D: Scene-Adaptive Reference Point Refinement for Sparse 3D Object Detection

Fan Li, Jing Lu, Yunlu Xu, Changhong Wu, Tao Xu, Zhaoyi Xiang, Yi Niu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (8) · 6073-6081

DOI: 10.1609/aaai.v40i8.37531 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Fan Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sparse query-based detectors have emerged as the dominant paradigm in camera-only 3D object detection, owing to their exceptional performance and computational efficiency. A central component of these approaches is the use of reference points, which serve as learnable spatial anchors to guide queries in localizing target objects. However, existing methods typically employ a unified set of reference points across all scenes, a design we find suboptimal for handling complex scenarios with highly imbalanced object distributions, such as road intersections or occluded environments. In this paper, we investigate the adaptability of reference points and propose Refine3D, an adaptive refinement mechanism that achieves scene-level alignment between the distribution of reference points and ground-truth objects. In particular, we introduce a novel Reference Point Distribution Loss (RPD-Loss) to ensure reference points converge globally toward object positions, and a Scene-Adaptive Refinement head (SAR-Head) that predicts dynamic offsets for each reference point. Both components can be seamlessly integrated into mainstream sparse detectors. Extensive experiments on two challenging autonomous driving datasets demonstrate that Refine3D outperforms the state-of-the-art with improved detection accuracy and robustness.

Zitieren

APA

Li, F., Lu, J., Xu, Y., Wu, C., Xu, T., Xiang, Z., & Niu, Y. (2026). Refine3D: Scene-Adaptive Reference Point Refinement for Sparse 3D Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 40(8), 6073-6081. https://doi.org/10.1609/aaai.v40i8.37531

Vancouver

Li F, Lu J, Xu Y, Wu C, Xu T, Xiang Z, et al. Refine3D: Scene-Adaptive Reference Point Refinement for Sparse 3D Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(8):6073-6081. doi:10.1609/aaai.v40i8.37531

BibTeX
@article{Li2026,
  author = {Li, Fan and Lu, Jing and Xu, Yunlu and Wu, Changhong and Xu, Tao and Xiang, Zhaoyi and Niu, Yi},
  title = {Refine3D: Scene-Adaptive Reference Point Refinement for Sparse 3D Object Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {8},
  pages = {6073--6081},
  doi = {10.1609/aaai.v40i8.37531}
}
Kostenlos starten →