mlsanityData to 7 Oct 2026

VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking

arXiv 2303.11301 ↗First posted 20 Mar 2023cs.CVcited by 221

Not on the map. Why?

Abstract (arXiv)

3D object detectors usually rely on hand-crafted proxies, e.g., anchors or centers, and translate well-studied 2D frameworks to 3D. Thus, sparse voxel features need to be densified and processed by dense prediction heads, which inevitably costs extra computation. In this paper, we instead propose VoxelNext for fully sparse 3D object detection. Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies. Our strong sparse convolutional network VoxelNeXt detects and tracks 3D objects through voxel features entirely. It is an elegant and efficient framework, with no need for sparse-to-dense conversion or NMS post-processing. Our method achieves a better speed-accuracy trade-off than other mainframe detectors on the nuScenes dataset. For the first time, we show that a fully sparse voxel-based representation works decently for LIDAR 3D object detection and tracking. Extensive experiments on nuScenes, Waymo, and Argoverse2 benchmarks validate the effectiveness of our approach. Without bells and whistles, our model outperforms all existing LIDAR methods on the nuScenes tracking test benchmark.

Key facts. Cited by 221 papers in the map (data through 7 Oct 2026). Builds on 55 of its 63 references that are in the map. First posted on arXiv 20 Mar 2023.

Builds on

55 of 63 references.

References · 55

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  9. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  10. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  11. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  12. 2017Focal Loss for Dense Object Detectioncited by 749
38 more
  1. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  2. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
  3. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  4. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  5. 2020Tracking Objects as Pointscited by 483
  6. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  7. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  8. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  9. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  10. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  11. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  12. 2021Voxel Transformer for 3D Object Detectioncited by 247
  13. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  14. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  15. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  16. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  17. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  18. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  19. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  20. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  21. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  22. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  23. 2021SimpleTrack: Understanding and Rethinking 3D Multi-object Trackingcited by 102
  24. 2022Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Cloudscited by 102
  25. 2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
  26. 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
  27. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  28. 2021Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 87
  29. 2019Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspotscited by 84
  30. 2022Fully Sparse 3D Object Detectioncited by 84
  31. 2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79
  32. 2021M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformerscited by 74
  33. 2020Probabilistic 3D Multi-Modal, Multi-Object Tracking for Autonomous Drivingcited by 73
  34. 20213D-MAN: 3D Multi-frame Attention Network for Object Detectioncited by 73
  35. 2022VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attentioncited by 48
  36. 2022Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graphcited by 42
  37. 2021Learnable Online Graph Representations for 3D Multi-Object Trackingcited by 38
  38. 2020InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modelingcited by 35

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 35; 2024: 82; 2025: 64; 2026: 40.

221 papers.

Sort:

By area:

  1. 2024GenAD: Generative End-to-End Autonomous Drivingcited by 225
  2. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 166
  3. 2023UniPAD: A Universal Pre-training Paradigm for Autonomous Drivingcited by 73
  4. 2023Far3D: Expanding the Horizon for Surround-view 3D Object Detectioncited by 70
  5. 2024Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detectioncited by 66
  6. 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 65
  7. 2023FocalFormer3D : Focusing on Hard Instance for 3D Object Detectioncited by 58
  8. 2024IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detectioncited by 57
  9. 2023PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigmcited by 56
  10. 2024Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysiscited by 52
  11. 2024SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detectioncited by 52
  12. 2023PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Predictioncited by 51
38 more
  1. 2024SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Drivingcited by 46
  2. 2023A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineeringcited by 45
  3. 2023HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Cloudscited by 45
  4. 2023SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentationcited by 44
  5. 2023SAM3D: Zero-Shot 3D Object Detection via Segment Anything Modelcited by 40
  6. 2024LION: Linear Group RNN for 3D Object Detection in Point Cloudscited by 38
  7. 2025Multimodal Fusion and Vision-Language Models: A Survey for Robot Visioncited by 37
  8. 2023BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detectioncited by 35
  9. 2023FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxelscited by 34
  10. 2024GaussianAD: Gaussian-Centric End-to-End Autonomous Drivingcited by 31
  11. 2023Fully Sparse Fusion for 3D Object Detectioncited by 29
  12. 2024LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detectioncited by 29
  13. 2024TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learningcited by 29
  14. 2023Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detectioncited by 28
  15. 2023Uni3DETR: Unified 3D Detection Transformercited by 26
  16. 2024MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detectioncited by 23
  17. 2023Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?cited by 22
  18. 2024Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectivescited by 22
  19. 2024Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimationcited by 22
  20. 2024OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagationcited by 19
  21. 2024SEED: A Simple and Effective 3D DETR in Point Cloudscited by 19
  22. 2024RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusioncited by 19
  23. 2023Instance Tracking in 3D Scenes from Egocentric Videoscited by 17
  24. 2024Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehensioncited by 17
  25. 2024MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Drivingcited by 17
  26. 2025TSP3D: Text-guided Sparse Voxel Pruning for Efficient 3D Visual Groundingcited by 17
  27. 2025SparseAlign: A Fully Sparse Framework for Cooperative Object Detectioncited by 15
  28. 2023MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detectioncited by 14
  29. 2024VoxelNextFusion: A Simple, Unified and Effective Voxel Fusion Framework for Multi-Modal 3D Object Detectioncited by 14
  30. 2024Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encodercited by 14
  31. 2024MSSF: A 4D Radar and Camera Fusion Framework With Multi-Stage Sampling for 3D Object Detection in Autonomous Drivingcited by 14
  32. 2025AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splattingcited by 14
  33. 2025Data Scaling Laws for End-to-End Autonomous Drivingcited by 14
  34. 2023FusionFormer: A Multi-sensory Fusion in Bird's-Eye-View and Temporal Consistent Transformer for 3D Object Detectioncited by 13
  35. 2024ContrastAlign: Toward Robust BEV Feature Alignment via Contrastive Learning for Multi-Modal 3D Object Detectioncited by 13
  36. 20243DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for Indoor 3D Object Detectioncited by 13
  37. 2025DriveGEN: Generalized and Robust 3D Detection in Driving via Controllable Text-to-Image Diffusion Generationcited by 13
  38. 2025RefAV: Towards Planning-Centric Scenario Miningcited by 13

50 most cited of 221 All 221 (JSON)