RangeRCNN: Towards Fast and Accurate 3D Object Detection with Range Image Representation

TL;DR

RangeRCNN introduces a novel 3D object detection framework leveraging range image representation, combining dense 2D convolution with scale-adaptive modules and a two-stage RCNN, achieving state-of-the-art results efficiently.

Contribution

The paper proposes a new range image-based 3D detection method with a scale-adaptive module and a two-stage RCNN, improving efficiency and accuracy over voxel and point-based methods.

Findings

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

Demonstrates real-time detection capabilities.

Introduces effective data augmentation for range images.

Abstract

We present RangeRCNN, a novel and effective 3D object detection framework based on the range image representation. Most existing methods are voxel-based or point-based. Though several optimizations have been introduced to ease the sparsity issue and speed up the running time, the two representations are still computationally inefficient. Compared to them, the range image representation is dense and compact which can exploit powerful 2D convolution. Even so, the range image is not preferred in 3D object detection due to scale variation and occlusion. In this paper, we utilize the dilated residual block (DRB) to better adapt different object scales and obtain a more flexible receptive field. Considering scale variation and occlusion, we propose the RV-PV-BEV (range view-point view-bird's eye view) module to transfer features from RV to BEV. The anchor is defined in BEV which avoids scale variation and occlusion. Neither RV nor BEV can provide enough information for height estimation; therefore, we propose a two-stage RCNN for better 3D detection performance. The aforementioned point view not only serves as a bridge from RV to BEV but also provides pointwise features for RCNN. Experiments show that RangeRCNN achieves state-of-the-art performance on the KITTI dataset and the Waymo Open dataset, and provides more possibilities for real-time 3D object detection. We further introduce and discuss the data augmentation strategy for the range image based method, which will be very valuable for future research on range image.