mlsanityData to 7 Oct 2026

To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels

arXiv 2106.13381 ↗First posted 25 Jun 2021cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

3D object detection is vital for many robotics applications. For tasks where a 2D perspective range image exists, we propose to learn a 3D representation directly from this range image view. To this end, we designed a 2D convolutional network architecture that carries the 3D spherical coordinates of each pixel throughout the network. Its layers can consume any arbitrary convolution kernel in place of the default inner product kernel and exploit the underlying local geometry around each pixel. We outline four such kernels: a dense kernel according to the bag-of-words paradigm, and three graph kernels inspired by recent graph neural network advances: the Transformer, the PointNet, and the Edge Convolution. We also explore cross-modality fusion with the camera image, facilitated by operating in the perspective range image view. Our method performs competitively on the Waymo Open Dataset and improves the state-of-the-art AP for pedestrian detection from 69.7% to 75.5%. It is also efficient in that our smallest model, which still outperforms the popular PointPillars in quality, requires 180 times fewer FLOPS and model parameters

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 29 of its 34 references that are in the map. First posted on arXiv 25 Jun 2021.

Builds on

29 of 34 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  9. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  10. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  11. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  12. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
17 more
  1. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  2. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  3. 2019Objects as Pointscited by 1,172
  4. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  5. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  6. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  7. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  8. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  9. 2017Submanifold Sparse Convolutional Networkscited by 223
  10. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  11. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  12. 2019LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Drivingcited by 133
  13. 2016Vehicle Detection from 3D Lidar Using Fully Convolutional Networkcited by 105
  14. 2020Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detectioncited by 78
  15. 2019StarNet: Targeted Computation for Object Detection in Point Cloudscited by 46
  16. 2020An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Cloudscited by 45
  17. 2020Improving 3D Object Detection through Progressive Population Based Augmentationcited by 41

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 13; 2023: 12; 2024: 9; 2025: 1; 2026: 1.

39 papers.

Sort:

By area:

  1. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
  2. 2022FUTR3D: A Unified Sensor Fusion Framework for 3D Detectioncited by 194
  3. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  4. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  5. 2022DeepInteraction: 3D Object Detection via Modality Interactioncited by 125
  6. 2022Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Cloudscited by 102
  7. 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
  8. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  9. 2022Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completioncited by 82
  10. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generationcited by 45
  11. 2022Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graphcited by 42
  12. 2022DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detectioncited by 39
27 more
  1. 2023Learning Occupancy for Monocular 3D Object Detectioncited by 35
  2. 2024Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformercited by 26
  3. 2023PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformercited by 21
  4. 2024DeepInteraction++: Multi-Modality Interaction for Autonomous Drivingcited by 15
  5. 2023DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Cloudscited by 14
  6. 2025GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attentioncited by 14
  7. 2023Curricular Object Manipulation in LiDAR-based Object Detectioncited by 12
  8. 2022Li3DeTr: A LiDAR based 3D Detection Transformercited by 11
  9. 2023PARTNER: Level up the Polar Representation for LiDAR 3D Object Detectioncited by 9
  10. 2023An Empirical Analysis of Range for 3D Object Detectioncited by 9
  11. 2024CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformercited by 7
  12. 2024Towards Stable 3D Object Detectioncited by 7
  13. 2024Improving Distant 3D Object Detection Using 2D Box Supervisioncited by 6
  14. 2022Transformers Meet Visual Learning Understanding: A Comprehensive Reviewcited by 5
  15. 2022Context-Aware Data Augmentation for LIDAR 3D Object Detectioncited by 5
  16. 2022LidarNAS: Unifying and Searching Neural Architectures for 3D Point Cloudscited by 4
  17. 2024Small, Versatile and Mighty: A Range-View Perception Frameworkcited by 4
  18. 2022Cost-Aware Evaluation and Model Scaling for LiDAR-Based 3D Object Detectioncited by 3
  19. 2023Efficient Transformer-based 3D Object Detection with Dynamic Token Haltingcited by 3
  20. 2023Link Prediction for Flow-Driven Spatial Networkscited by 3
  21. 2024PVTransformer: Point-to-Voxel Transformer for Scalable 3D Object Detectioncited by 3
  22. 2023LEF: Late-to-Early Temporal Fusion for LiDAR 3D Object Detectioncited by 2
  23. 2023Multimodal Object Query Initialization for 3D Object Detectioncited by 2
  24. 2023GLiDR: Topologically Regularized Graph Generative Network for Sparse LiDAR Point Cloudscited by 2
  25. 2021SoK: Vehicle Orientation Representations for Deep Rotation Estimationcited by 1
  26. 2026GEM: Generating LiDAR World Model via Deformable Mambacited by 1
  27. 2024What Matters in Range View 3D Object Detectioncited by 0