3D Cascade RCNN: High Quality Object Detection in Point Clouds

TL;DR

This paper introduces 3D Cascade RCNN, a novel cascade architecture for high-quality 3D object detection in sparse LiDAR point clouds, utilizing point completeness-aware re-weighting to improve detection accuracy.

Contribution

It proposes a new cascade detection framework for 3D point clouds that incorporates point completeness as a task weight, enhancing detection quality without extra computational cost.

Findings

Outperforms state-of-the-art methods on KITTI and Waymo datasets.

Effectively handles sparse point cloud data with completeness-aware re-weighting.

Demonstrates significant improvements in 3D detection accuracy.

Abstract

Recent progress on 2D object detection has featured Cascade RCNN, which capitalizes on a sequence of cascade detectors to progressively improve proposal quality, towards high-quality object detection. However, there has not been evidence in support of building such cascade structures for 3D object detection, a challenging detection scenario with highly sparse LiDAR point clouds. In this work, we present a simple yet effective cascade architecture, named 3D Cascade RCNN, that allocates multiple detectors based on the voxelized point clouds in a cascade paradigm, pursuing higher quality 3D object detector progressively. Furthermore, we quantitatively define the sparsity level of the points within 3D bounding box of each object as the point completeness score, which is exploited as the task weight for each proposal to guide the learning of each stage detector. The spirit behind is to assign higher weights for high-quality proposals with relatively complete point distribution, while down-weight the proposals with extremely sparse points that often incur noise during training. This design of completeness-aware re-weighting elegantly upgrades the cascade paradigm to be better applicable for the sparse input data, without increasing any FLOP budgets. Through extensive experiments on both the KITTI dataset and Waymo Open Dataset, we validate the superiority of our proposed 3D Cascade RCNN, when comparing to state-of-the-art 3D object detection techniques. The source code is publicly available at \url{https://github.com/caiqi/Cascasde-3D}.