Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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\footnote{\url{https://github.com/jialeli1/From-Voxel-to-Point}}.

Jiale Li, Hang Dai, Ling Shao, Yong Ding• 2021

Related benchmarks

TaskDatasetResultRank
3D Object DetectionWaymo Open Dataset (val)--
175
Vehicle DetectionWaymo Open Dataset LEVEL_1 v1.2 (val)
3D AP77.24
28
Bird's Eye View Object Detection (Pedestrian)KITTI (test)
AP (Easy)56.54
27
Vehicle DetectionWaymo Open Dataset LEVEL_2 v1.2 (val)
3D AP0.6977
22
3D Object DetectionKITTI Pedestrian official (test)
AP (Easy)51.8
19
Showing 5 of 5 rows

Other info

Follow for update