mlsanityData to 7 Oct 2026

OcTr: Octree-based Transformer for 3D Object Detection

arXiv 2303.12621 ↗First posted 22 Mar 2023cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

A key challenge for LiDAR-based 3D object detection is to capture sufficient features from large scale 3D scenes especially for distant or/and occluded objects. Albeit recent efforts made by Transformers with the long sequence modeling capability, they fail to properly balance the accuracy and efficiency, suffering from inadequate receptive fields or coarse-grained holistic correlations. In this paper, we propose an Octree-based Transformer, named OcTr, to address this issue. It first constructs a dynamic octree on the hierarchical feature pyramid through conducting self-attention on the top level and then recursively propagates to the level below restricted by the octants, which captures rich global context in a coarse-to-fine manner while maintaining the computational complexity under control. Furthermore, for enhanced foreground perception, we propose a hybrid positional embedding, composed of the semantic-aware positional embedding and attention mask, to fully exploit semantic and geometry clues. Extensive experiments are conducted on the Waymo Open Dataset and KITTI Dataset, and OcTr reaches newly state-of-the-art results.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 59 of its 66 references that are in the map. First posted on arXiv 22 Mar 2023.

Builds on

59 of 66 references.

References · 59

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  8. 2020Longformer: The Long-Document Transformercited by 3,362
  9. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  10. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  12. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
38 more
  1. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  2. 2020Rethinking Attention with Performerscited by 1,584
  3. 2020Point Transformercited by 1,462
  4. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  5. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  6. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  7. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  8. 2017Focal Loss for Dense Object Detectioncited by 749
  9. 2020PCT: Point cloud transformercited by 730
  10. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  11. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  12. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  13. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  14. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  15. 2021Early Convolutions Help Transformers See Bettercited by 395
  16. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  17. 2022Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizationscited by 359
  18. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  19. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  20. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  21. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  22. 2021Voxel Transformer for 3D Object Detectioncited by 247
  23. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  24. 20203D Object Detection with Pointformercited by 194
  25. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  26. 2019Blockwise Self-Attention for Long Document Understandingcited by 158
  27. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  28. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  29. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  30. 2022QuadTree Attention for Vision Transformerscited by 129
  31. 2020End-to-End Object Detection with Adaptive Clustering Transformercited by 109
  32. 2021Improving 3D Object Detection with Channel-wise Transformercited by 108
  33. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  34. 2021Fast Point Transformercited by 103
  35. 2022Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Cloudscited by 102
  36. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  37. 2022Fully Sparse 3D Object Detectioncited by 84
  38. 2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 10; 2025: 13; 2026: 3.

32 papers.

Sort:

By area:

  1. 2024IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detectioncited by 57
  2. 2023OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queriescited by 48
  3. 2023HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Cloudscited by 45
  4. 2024LION: Linear Group RNN for 3D Object Detection in Point Cloudscited by 38
  5. 2023SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detectioncited by 30
  6. 2024Vision-based 3D occupancy prediction in autonomous driving: a review and outlookcited by 29
  7. 2024AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizercited by 28
  8. 2025CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridizationcited by 27
  9. 2024SEED: A Simple and Effective 3D DETR in Point Cloudscited by 19
  10. 2025APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformerscited by 17
  11. 2025FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximationcited by 16
  12. 2024ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attentioncited by 11
20 more
  1. 2025UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detectioncited by 10
  2. 2025HOTFormerLoc: Hierarchical Octree Transformer for Versatile Lidar Place Recognition Across Ground and Aerial Viewscited by 8
  3. 2024STAL3D: Unsupervised Domain Adaptation for 3D Object Detection via Collaborating Self-Training and Adversarial Learningcited by 6
  4. 2024FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detectioncited by 6
  5. 2023FusionViT: Hierarchical 3D Object Detection via LiDAR-Camera Vision Transformer Fusioncited by 5
  6. 2025Unified Cross-Scale 3D Generation and Understanding via Autoregressive Modelingcited by 5
  7. 2025Multistream Network for LiDAR and Camera-based 3D Object Detection in Outdoor Scenescited by 2
  8. 2025Towards Open-Vocabulary Multimodal 3D Object Detection with Attributescited by 2
  9. 2024Leveraging Anchor-based LiDAR 3D Object Detection via Point Assisted Sample Selectioncited by 1
  10. 2025IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformerscited by 1
  11. 2023SDVRF: Sparse-to-Dense Voxel Region Fusion for Multi-modal 3D Object Detectioncited by 0
  12. 2023R2Det: Redemption from Range-view for Accurate 3D Object Detectioncited by 0
  13. 2024Decoupled and Interactive Regression Modeling for High-performance One-stage 3D Object Detectioncited by 0
  14. 2025An Investigation of Beam Density on LiDAR Object Detection Performancecited by 0
  15. 2025FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devicescited by 0
  16. 2025Voxel Densification for Serialized 3D Object Detection: Mitigating Sparsity via Pre-serialization Expansioncited by 0
  17. 2025TransBridge: Boost 3D Object Detection by Scene-Level Completion with Transformer Decodercited by 0
  18. 2026RayMamba: Ray-Aligned Serialization for Long-Range 3D Object Detectioncited by 0
  19. 2026Comprehensive Robustness Analysis of LiDAR-based 3D Object Detection in Autonomous Drivingcited by 0
  20. 2026MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformerscited by 0