mlsanityData to 7 Oct 2026

R2Det: Redemption from Range-view for Accurate 3D Object Detection

arXiv 2307.11482 ↗First posted 21 Jul 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

LiDAR-based 3D object detection is of paramount importance for autonomous driving. Recent trends show a remarkable improvement for bird's-eye-view (BEV) based and point-based methods as they demonstrate superior performance compared to range-view counterparts. This paper presents an insight that leverages range-view representation to enhance 3D points for accurate 3D object detection. Specifically, we introduce a Redemption from Range-view Module (R2M), a plug-and-play approach for 3D surface texture enhancement from the 2D range view to the 3D point view. R2M comprises BasicBlock for 2D feature extraction, Hierarchical-dilated (HD) Meta Kernel for expanding the 3D receptive field, and Feature Points Redemption (FPR) for recovering 3D surface texture information. R2M can be seamlessly integrated into state-of-the-art LiDAR-based 3D object detectors as preprocessing and achieve appealing improvement, e.g., 1.39%, 1.67%, and 1.97% mAP improvement on easy, moderate, and hard difficulty level of KITTI val set, respectively. Based on R2M, we further propose R2Detector (R2Det) with the Synchronous-Grid RoI Pooling for accurate box refinement. R2Det outperforms existing range-view-based methods by a significant margin on both the KITTI benchmark and the Waymo Open Dataset. Codes will be made publicly available.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 42 of its 53 references that are in the map. First posted on arXiv 21 Jul 2023.

Builds on

42 of 53 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  5. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  6. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  7. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  8. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  9. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  10. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  11. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  12. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
30 more
  1. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  2. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  3. 2020Deep Continuous Fusion for Multi-Sensor 3D Object Detectioncited by 263
  4. 2021Voxel Transformer for 3D Object Detectioncited by 247
  5. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  6. 2017Submanifold Sparse Convolutional Networkscited by 223
  7. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  8. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  9. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  10. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  11. 2019LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Drivingcited by 133
  12. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  13. 2019Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detectioncited by 124
  14. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  15. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  16. 2016Vehicle Detection from 3D Lidar Using Fully Convolutional Networkcited by 105
  17. 2022Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Cloudscited by 102
  18. 2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79
  19. 2020Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detectioncited by 78
  20. 2020HDNET: Exploiting HD Maps for 3D Object Detectioncited by 78
  21. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  22. 2022SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detectioncited by 52
  23. 2021EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detectioncited by 49
  24. 2018IPOD: Intensive Point-based Object Detector for Point Cloudcited by 46
  25. 2020RangeRCNN: Towards Fast and Accurate 3D Object Detection with Range Image Representationcited by 37
  26. 2022CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detectioncited by 32
  27. 2023OcTr: Octree-based Transformer for 3D Object Detectioncited by 32
  28. 2023PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformercited by 21
  29. 2022Dense Voxel Fusion for 3D Object Detectioncited by 17
  30. 2022RangeSeg: Range-Aware Real Time Segmentation of 3D LiDAR Point Cloudscited by 11

Built on by

Not cited yet.