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

arXiv: https://arxiv.org/abs/2009.00206 · HTML: https://mlsanity.com/paper/2009.00206/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2020.

## Built on by (most cited first, 30 of 37)

- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [LiDAR R-CNN: An Efficient and Universal 3D Object Detector](https://mlsanity.com/paper/2103.15297/) (2021)
- [RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection](https://mlsanity.com/paper/2106.13365/) (2021)
- [FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detection](https://mlsanity.com/paper/2106.12449/) (2021)
- [SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection](https://mlsanity.com/paper/2304.14340/) (2023)
- [Multi-Modal 3D Object Detection in Autonomous Driving: a Survey](https://mlsanity.com/paper/2106.12735/) (2021)
- [FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation](https://mlsanity.com/paper/2312.04484/) (2023)
- [Towards Efficient 3D Object Detection with Knowledge Distillation](https://mlsanity.com/paper/2205.15156/) (2022)
- [SparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detection](https://mlsanity.com/paper/2403.07284/) (2024)
- [A Closer Look at Invariances in Self-supervised Pre-training for 3D Vision](https://mlsanity.com/paper/2207.04997/) (2022)
- [DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection](https://mlsanity.com/paper/2203.09510/) (2022)
- [MVFuseNet: Improving End-to-End Object Detection and Motion Forecasting through Multi-View Fusion of LiDAR Data](https://mlsanity.com/paper/2104.10772/) (2021)
- [Point2Seq: Detecting 3D Objects as Sequences](https://mlsanity.com/paper/2203.13394/) (2022)
- [LiDAR-CS Dataset: LiDAR Point Cloud Dataset with Cross-Sensors for 3D Object Detection](https://mlsanity.com/paper/2301.12515/) (2023)
- [Eliminating Cross-modal Conflicts in BEV Space for LiDAR-Camera 3D Object Detection](https://mlsanity.com/paper/2403.07372/) (2024)
- [Real-Time And Robust 3D Object Detection with Roadside LiDARs](https://mlsanity.com/paper/2207.05200/) (2022)
- [PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection](https://mlsanity.com/paper/2308.03982/) (2023)
- [LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations](https://mlsanity.com/paper/2210.13488/) (2022)
- [X-view: Non-egocentric Multi-View 3D Object Detector](https://mlsanity.com/paper/2103.13001/) (2021)
- [AugMapNet: Improving Spatial Latent Structure via BEV Grid Augmentation for Enhanced Vectorized Online HD Map Construction](https://mlsanity.com/paper/2503.13430/) (2025)
- [MBDF-Net: Multi-Branch Deep Fusion Network for 3D Object Detection](https://mlsanity.com/paper/2108.12863/) (2021)
- [Context-Aware Data Augmentation for LIDAR 3D Object Detection](https://mlsanity.com/paper/2211.10850/) (2022)
- [HALS: A Height-Aware Lidar Super-Resolution Framework for Autonomous Driving](https://mlsanity.com/paper/2202.03901/) (2022)
- [Survey and Systematization of 3D Object Detection Models and Methods](https://mlsanity.com/paper/2201.09354/) (2022)
- [CVFNet: Real-time 3D Object Detection by Learning Cross View Features](https://mlsanity.com/paper/2203.06585/) (2022)
- [Efficient Transformer-based 3D Object Detection with Dynamic Token Halting](https://mlsanity.com/paper/2303.05078/) (2023)
- [LiDAR-Based 3D Object Detection via Hybrid 2D Semantic Scene Generation](https://mlsanity.com/paper/2304.01519/) (2023)
- [OverlapMamba: Novel Shift State Space Model for LiDAR-based Place Recognition](https://mlsanity.com/paper/2405.07966/) (2024)
- [3D Object Detection Combining Semantic and Geometric Features from Point Clouds](https://mlsanity.com/paper/2110.04704/) (2021)
- [Cross-Cluster Shifting for Efficient and Effective 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/2403.06166/) (2024)

## Abstract (arXiv)

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.