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

TL;DR

This paper introduces an IoU-guided 3D object detection framework that combines voxel and point features with a novel decoder and RoI alignment, significantly improving detection accuracy on KITTI and Waymo datasets.

Contribution

The paper proposes a residual voxel-to-point decoder and an IoU alignment method for enhanced 3D object detection accuracy.

Findings

Achieves state-of-the-art results on KITTI and Waymo datasets.

Improves box recall and localization precision.

Demonstrates effectiveness of voxel-to-point feature integration.

Abstract

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}}.