mlsanityData to 7 Oct 2026

Deep Learning Based 3D Segmentation: A Survey

arXiv 2103.05423 ↗First posted 9 Mar 2021cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

3D segmentation is a fundamental and challenging problem in computer vision with applications in autonomous driving and robotics. It has received significant attention from the computer vision, graphics and machine learning communities. Conventional methods for 3D segmentation, based on hand-crafted features and machine learning classifiers, lack generalization ability. Driven by their success in 2D computer vision, deep learning techniques have recently become the tool of choice for 3D segmentation tasks. This has led to an influx of many methods in the literature that have been evaluated on different benchmark datasets. Whereas survey papers on RGB-D and point cloud segmentation exist, there is a lack of a recent in-depth survey that covers all 3D data modalities and application domains. This paper fills the gap and comprehensively surveys the recent progress in deep learning-based 3D segmentation techniques. We cover over 220 works from the last six years, analyze their strengths and limitations, and discuss their competitive results on benchmark datasets. The survey provides a summary of the most commonly used pipelines and finally highlights promising research directions for the future.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 117 of its 258 references that are in the map. First posted on arXiv 9 Mar 2021.

Builds on

117 of 258 references.

References · 117

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2017Mask R-CNNcited by 7,259
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  8. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  9. 2020Point Transformercited by 1,462
  10. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  11. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  12. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
38 more
  1. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  2. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  3. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  4. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  5. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  6. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  7. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  8. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  9. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  10. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  11. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  12. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  13. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  14. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  15. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  16. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  17. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  18. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  19. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  20. 20183D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanscited by 216
  21. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  22. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  23. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  24. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  25. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  26. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  27. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 168
  28. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  29. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  30. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  31. 2019Learning Object Bounding Boxes for 3D Instance Segmentation on Point Cloudscited by 156
  32. 2018GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloudcited by 145
  33. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  34. 20203D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentationcited by 140
  35. 2016SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networkscited by 134
  36. 2017Pointwise Convolutional Neural Networkscited by 126
  37. 2014Learning Rich Features from RGB-D Images for Object Detection and Segmentationcited by 124
  38. 20183DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentationcited by 118

50 most cited of 117 All 117 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 11; 2023: 12; 2024: 3; 2025: 0; 2026: 3.

30 papers.

Sort:

By area:

  1. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  2. 2023Vision Language Models in Autonomous Driving: A Survey and Outlookcited by 124
  3. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  4. 2023Grounding 3D Object Affordance from 2D Interactions in Imagescited by 62
  5. 20223D Vision with Transformers: A Surveycited by 21
  6. 2024CloSe: A 3D Clothing Segmentation Dataset and Modelcited by 21
  7. 2024Scalable 3D Panoptic Segmentation As Superpoint Graph Clusteringcited by 14
  8. 2022NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Cloudscited by 12
  9. 2022Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanicscited by 11
  10. 2023Leveraging VLM-Based Pipelines to Annotate 3D Objectscited by 10
  11. 2022DA Wand: Distortion-Aware Selection using Neural Mesh Parameterizationcited by 9
  12. 2023A Review of Panoptic Segmentation for Mobile Mapping Point Cloudscited by 8
18 more
  1. 2022SARNet: Semantic Augmented Registration of Large-Scale Urban Point Cloudscited by 5
  2. 2023On the Calibration of Uncertainty Estimation in LiDAR-based Semantic Segmentationcited by 5
  3. 2023HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labelingcited by 3
  4. 2023MeT: A Graph Transformer for Semantic Segmentation of 3D Meshescited by 3
  5. 2022Self-Supervised Contrastive Representation Learning for 3D Mesh Segmentationcited by 2
  6. 2022Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentationcited by 2
  7. 2022Learning 3D Semantics from Pose-Noisy 2D Images with Hierarchical Full Attention Networkcited by 1
  8. 2022On the calibration of underrepresented classes in LiDAR-based semantic segmentationcited by 1
  9. 2026Cross-View Urban Traffic Dataset: Drone-Supervised Ground Truth for Monocular Bird's-Eye View Localizationcited by 1
  10. 2022Generating 3D Bio-Printable Patches Using Wound Segmentation and Reconstruction to Treat Diabetic Foot Ulcerscited by 0
  11. 2023SSS3D: Fast Neural Architecture Search For Efficient Three-Dimensional Semantic Segmentationcited by 0
  12. 2023When ChatGPT for Computer Vision Will Come? From 2D to 3Dcited by 0
  13. 2023Contextualising Implicit Representations for Semantic Taskscited by 0
  14. 2023Geometry Aware Field-to-field Transformations for 3D Semantic Segmentationcited by 0
  15. 2023MSFormer: A Skeleton-multiview Fusion Method For Tooth Instance Segmentationcited by 0
  16. 2024ARCH2S: Dataset, Benchmark and Challenges for Learning Exterior Architectural Structures from Point Cloudscited by 0
  17. 2026MME: Mixture of Mesh Experts with Random Walk Transformer Gatingcited by 0
  18. 2026RGB-Pointmap Pretraining for Unified 3D Scene Understandingcited by 0