mlsanityData to 14 Oct 2026

SVQNet: Sparse Voxel-Adjacent Query Network for 4D Spatio-Temporal LiDAR Semantic Segmentation

arXiv 2308.13323 ↗First posted 25 Aug 2023cs.CV cs.ROcited by 14

Not on the map. Why?

Abstract (arXiv)

LiDAR-based semantic perception tasks are critical yet challenging for autonomous driving. Due to the motion of objects and static/dynamic occlusion, temporal information plays an essential role in reinforcing perception by enhancing and completing single-frame knowledge. Previous approaches either directly stack historical frames to the current frame or build a 4D spatio-temporal neighborhood using KNN, which duplicates computation and hinders realtime performance. Based on our observation that stacking all the historical points would damage performance due to a large amount of redundant and misleading information, we propose the Sparse Voxel-Adjacent Query Network (SVQNet) for 4D LiDAR semantic segmentation. To take full advantage of the historical frames high-efficiently, we shunt the historical points into two groups with reference to the current points. One is the Voxel-Adjacent Neighborhood carrying local enhancing knowledge. The other is the Historical Context completing the global knowledge. Then we propose new modules to select and extract the instructive features from the two groups. Our SVQNet achieves state-of-the-art performance in LiDAR semantic segmentation of the SemanticKITTI benchmark and the nuScenes dataset.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 43 of its 51 references that are in the map. First posted on arXiv 25 Aug 2023.

Builds on

43 of 51 references.

References · 43

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  7. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  8. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  9. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 423
  10. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 389
  11. 2018Context Encoding for Semantic Segmentationcited by 290
  12. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 275
31 more
  1. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 242
  2. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 223
  3. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  4. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  5. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 166
  6. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  7. 2020FLOT: Scene Flow on Point Clouds Guided by Optimal Transportcited by 129
  8. 2022Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentationcited by 119
  9. 2019MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequencescited by 117
  10. 2020MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Mapscited by 100
  11. 2021TPCN: Temporal Point Cloud Networks for Motion Forecastingcited by 94
  12. 2022TorchSparse: Efficient Point Cloud Inference Enginecited by 73
  13. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 72
  14. 20214D Panoptic LiDAR Segmentationcited by 65
  15. 2021Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Datacited by 64
  16. 2021Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perceptioncited by 57
  17. 2020Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Drivingcited by 55
  18. 2020An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Cloudscited by 45
  19. 2022Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutionscited by 35
  20. 20224D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregationcited by 35
  21. 2021LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignmentcited by 26
  22. 2020DeepLiDARFlow: A Deep Learning Architecture For Scene Flow Estimation Using Monocular Camera and Sparse LiDARcited by 24
  23. 2022Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregationcited by 23
  24. 2021DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentationcited by 22
  25. 2022CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentationcited by 15
  26. 2020MoNet: Motion-based Point Cloud Prediction Networkcited by 14
  27. 2019DeepTemporalSeg: Temporally Consistent Semantic Segmentation of 3D LiDAR Scanscited by 13
  28. 2020Anchor-Based Spatio-Temporal Attention 3D Convolutional Networks for Dynamic 3D Point Cloud Sequencescited by 9
  29. 2022Abstract Flow for Temporal Semantic Segmentation on the Permutohedral Latticecited by 9
  30. 2020ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentationcited by 8
  31. 2021Temp-Frustum Net: 3D Object Detection with Temporal Fusioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 6; 2026: 2.

14 papers.

Sort:

By area:

  1. 2024RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentationcited by 15
  2. 2024TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentationcited by 13
  3. 2025MutualForce: Mutual-Aware Enhancement for 4D Radar-LiDAR 3D Object Detectioncited by 6
  4. 2025Zero-Shot 4D Lidar Panoptic Segmentationcited by 6
  5. 2023NSM4D: Neural Scene Model Based Online 4D Point Cloud Sequence Understandingcited by 5
  6. 2024SegNet4D: Efficient Instance-Aware 4D Semantic Segmentation for LiDAR Point Cloudcited by 5
  7. 2025nuScenes Revisited: Progress and Challenges in Autonomous Drivingcited by 2
  8. 2024Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic Segmentationcited by 1
  9. 2024P3P: Pseudo-3D Pre-training for Scaling 3D Voxel-based Masked Autoencoderscited by 0
  10. 20254D-CS: Exploiting Cluster Prior for 4D Spatio-Temporal LiDAR Semantic Segmentationcited by 0
  11. 2025Domain Adaptation-Based Crossmodal Knowledge Distillation for 3D Semantic Segmentationcited by 0
  12. 20254DSegStreamer: Streaming 4D Panoptic Segmentation via Dual Threadscited by 0
2 more
  1. 2026UniD-Shift: Towards Unified Semantic Segmentation via Interpretable Share-Private Multimodal Decompositioncited by 0
  2. 2026MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Bufferscited by 0