mlsanityData to 14 Oct 2026

3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

arXiv 1711.10275 ↗First posted 28 Nov 2017cs.CVcited by 748

Not on the map. Why?

Abstract (arXiv)

Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally dense (e.g., photos), many other data sources are inherently sparse. Examples include 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard "dense" implementations of convolutional networks are very inefficient when applied on such sparse data. We introduce new sparse convolutional operations that are designed to process spatially-sparse data more efficiently, and use them to develop spatially-sparse convolutional networks. We demonstrate the strong performance of the resulting models, called submanifold sparse convolutional networks (SSCNs), on two tasks involving semantic segmentation of 3D point clouds. In particular, our models outperform all prior state-of-the-art on the test set of a recent semantic segmentation competition.

Key facts. Cited by 748 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 135; 2022: 178; 2023: 173; 2024: 119; 2025: 90; 2026: 53.

748 papers.

Sort:

By area:

  1. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
  2. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  3. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  4. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
  5. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
  6. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 303
  7. 2023OpenMask3D: Open-Vocabulary 3D Instance Segmentationcited by 289
  8. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
  9. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 267
  10. 2023NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenariocited by 262
  11. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 246
  12. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
38 more
  1. 2024GenAD: Generative End-to-End Autonomous Drivingcited by 225
  2. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 222
  3. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  4. 2022Omnivore: A Single Model for Many Visual Modalitiescited by 215
  5. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  6. 2023ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understandingcited by 202
  7. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 200
  8. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 179
  9. 2022PLA: Language-Driven Open-Vocabulary 3D Scene Understandingcited by 177
  10. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 167
  11. 2021Multimodal Virtual Point 3D Detectioncited by 166
  12. 2023Towards Open Vocabulary Learning: A Surveycited by 166
  13. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 158
  14. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  15. 2021InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referringcited by 141
  16. 2024SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understandingcited by 133
  17. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  18. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 127
  19. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  20. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 125
  21. 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 124
  22. 2023Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidancecited by 124
  23. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  24. 2023DSVT: Dynamic Sparse Voxel Transformer with Rotated Setscited by 122
  25. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  26. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  27. 2022Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generationcited by 119
  28. 2022Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentationcited by 119
  29. 2022AEGNN: Asynchronous Event-based Graph Neural Networkscited by 118
  30. 2022Superpoint Transformer for 3D Scene Instance Segmentationcited by 116
  31. 2024Grounded 3D-LLM with Referent Tokenscited by 115
  32. 20223D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selectioncited by 110
  33. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 110
  34. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 109
  35. 2022K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditionscited by 108
  36. 2022ConvMAE: Masked Convolution Meets Masked Autoencoderscited by 105
  37. 2021Fast Point Transformercited by 104
  38. 2021Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networkscited by 99

50 most cited of 748 All 748 (JSON)