From Voxel to Point: IoU-Guided 3D Object Detection for Point Cloud with Voxel-to-Point Decoder

Li, J., Dai, H., Shao, L. and Ding, Y. (2021) From Voxel to Point: IoU-Guided 3D Object Detection for Point Cloud with Voxel-to-Point Decoder. In: MM '21: Proceedings of the 29th ACM International Conference on Multimedia, Online, 20-24 Oct 2021, pp. 4622-4631. ISBN 9781450386517 (doi: 10.1145/3474085.3475314)

Full text not currently available from Enlighten.


In this paper, we present an Intersection-over-Union (IoU) guided two-stage 3D object detector with a voxel-to-point decoder. To preserve the necessary information from all raw points and maintain the high box recall in voxel based Region Proposal Network (RPN), we propose a residual voxel-to-point decoder to extract the point features in addition to the map-view features from the voxel based RPN. We use a 3D Region of Interest (RoI) alignment to crop and align the features with the proposal boxes for accurately perceiving the object position. The RoI-Aligned features are finally aggregated with the corner geometry embeddings that can provide the potentially missing corner information in the box refinement stage. We propose a simple and efficient method to align the estimated IoUs to the refined proposal boxes as a more relevant localization confidence. The comprehensive experiments on KITTI and Waymo Open Dataset demonstrate that our method achieves significant improvements with novel architectures against the existing methods. The code is available on Github URL .

Item Type:Conference Proceedings
Glasgow Author(s) Enlighten ID:Dai, Dr Hang
Authors: Li, J., Dai, H., Shao, L., and Ding, Y.
College/School:College of Science and Engineering > School of Computing Science

University Staff: Request a correction | Enlighten Editors: Update this record