VENet: Voting Enhancement Network for 3D object detection

Xie, Qian, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680, Wu, Jing ORCID: https://orcid.org/0000-0001-5123-9861, Wang, Zhoutao, Lu, Dening, Wei, Mingqiang and Wang, Jun 2021. VENet: Voting Enhancement Network for 3D object detection. Presented at: CVF/IEEE International Conference on Computer Vision (ICCV 2021), Virtual / Montreal, QC, Canada, 11-17 October 2021. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. IEEE, pp. 3692-3701. 10.1109/ICCV48922.2021.00369

PDF - Accepted Post-Print Version Download (1MB)

Abstract

Hough voting, as has been demonstrated in VoteNet, is effective for 3D object detection, where voting is a key step. In this paper, we propose a novel VoteNet-based 3D detector with vote enhancement to improve the detection accuracy in cluttered indoor scenes. It addresses the limitations of current voting schemes, i.e., votes from neighboring objects and background have significant negative impacts. Before voting, we replace the classic MLP with the proposed Attentive MLP (AMLP) in the backbone network to get better feature description of seed points. During voting, we design a new vote attraction loss (VALoss) to enforce vote centers to locate closely and compactly to the corresponding object centers. After voting, we then devise a vote weighting module to integrate the foreground/background prediction into the vote aggregation process to enhance the capability of the original VoteNet to handle noise from background voting. The three proposed strategies all contribute to more effective voting and improved performance, resulting in a novel 3D object detector, termed VENet. Experiments show that our method outperforms state-of-the-art methods on benchmark datasets. Ablation studies demonstrate the effectiveness of the proposed components.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	IEEE
ISBN:	9781665428132
ISSN:	1550-5499
Date of First Compliant Deposit:	2 September 2021
Last Modified:	21 Aug 2025 14:31
URI:	https://orca.cardiff.ac.uk/id/eprint/143843

Citation Data

Cited 12 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item