X-view: Non-egocentric Multi-View 3D Object Detector

TL;DR

X-view introduces a novel multi-view 3D detection paradigm that overcomes perspective view limitations, improving detection accuracy across various LiDAR-based 3D detectors with minimal computational overhead.

Contribution

The paper proposes X-view, a general multi-view 3D detection framework that relaxes perspective view constraints and enhances detection performance on multiple state-of-the-art methods.

Findings

X-view improves detection accuracy on KITTI and NuScenes datasets.

X-view enhances performance when combined with four mainstream 3D detectors.

X-view maintains minimal impact on runtime efficiency.

Abstract

3D object detection algorithms for autonomous driving reason about 3D obstacles either from 3D birds-eye view or perspective view or both. Recent works attempt to improve the detection performance via mining and fusing from multiple egocentric views. Although the egocentric perspective view alleviates some weaknesses of the birds-eye view, the sectored grid partition becomes so coarse in the distance that the targets and surrounding context mix together, which makes the features less discriminative. In this paper, we generalize the research on 3D multi-view learning and propose a novel multi-view-based 3D detection method, named X-view, to overcome the drawbacks of the multi-view methods. Specifically, X-view breaks through the traditional limitation about the perspective view whose original point must be consistent with the 3D Cartesian coordinate. X-view is designed as a general paradigm that can be applied on almost any 3D detectors based on LiDAR with only little increment of running time, no matter it is voxel/grid-based or raw-point-based. We conduct experiments on KITTI and NuScenes datasets to demonstrate the robustness and effectiveness of our proposed X-view. The results show that X-view obtains consistent improvements when combined with four mainstream state-of-the-art 3D methods: SECOND, PointRCNN, Part-A^2, and PV-RCNN.