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

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.

References in corpus (4)

• Deep Continuous Fusion for Multi-Sensor 3D Object Detection
• Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection
• Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud
• Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection

Cited by in corpus (8)

• CenterNet3D: An Anchor Free Object Detector for Point Cloud
• Multi-Modal 3D Object Detection in Autonomous Driving: a Survey
• MAFF-Net: Filter False Positive for 3D Vehicle Detection with Multi-modal Adaptive Feature Fusion
• FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detection
• RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection
• It's All Around You: Range-Guided Cylindrical Network for 3D Object Detection
• MBDF-Net: Multi-Branch Deep Fusion Network for 3D Object Detection
• LiDAR R-CNN: An Efficient and Universal 3D Object Detector