mlsanityData to 7 Oct 2026

Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection

arXiv 2005.09927 ↗First posted 20 May 2020cs.CV cs.LG cs.ROcited by 78

Not on the map. Why?

Abstract (arXiv)

This paper presents a novel 3D object detection framework that processes LiDAR data directly on its native representation: range images. Benefiting from the compactness of range images, 2D convolutions can efficiently process dense LiDAR data of a scene. To overcome scale sensitivity in this perspective view, a novel range-conditioned dilation (RCD) layer is proposed to dynamically adjust a continuous dilation rate as a function of the measured range. Furthermore, localized soft range gating combined with a 3D box-refinement stage improves robustness in occluded areas, and produces overall more accurate bounding box predictions. On the public large-scale Waymo Open Dataset, our method sets a new baseline for range-based 3D detection, outperforming multiview and voxel-based methods over all ranges with unparalleled performance at long range detection.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 29; 2023: 17; 2024: 12; 2025: 3; 2026: 1.

78 papers.

Sort:

By area:

  1. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
  2. 2021Voxel Transformer for 3D Object Detectioncited by 247
  3. 2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
  4. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  5. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  6. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 144
  7. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  8. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  9. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  10. 2022DeepInteraction: 3D Object Detection via Modality Interactioncited by 125
  11. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  12. 2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
38 more
  1. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  2. 2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 97
  3. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
  4. 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
  5. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  6. 2022Fully Sparse 3D Object Detectioncited by 84
  7. 2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79
  8. 2021M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformerscited by 74
  9. 20213D-MAN: 3D Multi-frame Attention Network for Object Detectioncited by 73
  10. 2022Motion Inspired Unsupervised Perception and Prediction in Autonomous Drivingcited by 59
  11. 2022Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Imagescited by 56
  12. 2022VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attentioncited by 48
  13. 2023HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Cloudscited by 45
  14. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generationcited by 45
  15. 20214D-Net for Learned Multi-Modal Alignmentcited by 44
  16. 2022Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graphcited by 42
  17. 2021To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernelscited by 39
  18. 2022DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detectioncited by 39
  19. 2023FastPillars: A Deployment-friendly Pillar-based 3D Detectorcited by 39
  20. 2023Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Drivingcited by 37
  21. 2023Learning Occupancy for Monocular 3D Object Detectioncited by 35
  22. 2021Pseudo-labeling for Scalable 3D Object Detectioncited by 32
  23. 2023Super Sparse 3D Object Detectioncited by 32
  24. 2022Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Drivingcited by 30
  25. 2022Towards Efficient 3D Object Detection with Knowledge Distillationcited by 29
  26. 2023Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detectioncited by 28
  27. 2024SparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detectioncited by 25
  28. 2022A Closer Look at Invariances in Self-supervised Pre-training for 3D Visioncited by 24
  29. 2023PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformercited by 21
  30. 2023Human-centric Scene Understanding for 3D Large-scale Scenarioscited by 17
  31. 2022Point2Seq: Detecting 3D Objects as Sequencescited by 15
  32. 2024DeepInteraction++: Multi-Modality Interaction for Autonomous Drivingcited by 15
  33. 2022INT: Towards Infinite-frames 3D Detection with An Efficient Frameworkcited by 14
  34. 2023MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequencescited by 13
  35. 2023Curricular Object Manipulation in LiDAR-based Object Detectioncited by 12
  36. 2021Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systemscited by 11
  37. 2024An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domainscited by 10
  38. 2024Progressive Multi-Modal Fusion for Robust 3D Object Detectioncited by 10

50 most cited of 78 All 78 (JSON)