mlsanityData to 7 Oct 2026

3D Shape Segmentation with Projective Convolutional Networks

arXiv 1612.02808 ↗First posted 8 Dec 2016cs.CV cs.GRcited by 63

Not on the map. Why?

Abstract (arXiv)

This paper introduces a deep architecture for segmenting 3D objects into their labeled semantic parts. Our architecture combines image-based Fully Convolutional Networks (FCNs) and surface-based Conditional Random Fields (CRFs) to yield coherent segmentations of 3D shapes. The image-based FCNs are used for efficient view-based reasoning about 3D object parts. Through a special projection layer, FCN outputs are effectively aggregated across multiple views and scales, then are projected onto the 3D object surfaces. Finally, a surface-based CRF combines the projected outputs with geometric consistency cues to yield coherent segmentations. The whole architecture (multi-view FCNs and CRF) is trained end-to-end. Our approach significantly outperforms the existing state-of-the-art methods in the currently largest segmentation benchmark (ShapeNet). Finally, we demonstrate promising segmentation results on noisy 3D shapes acquired from consumer-grade depth cameras.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 20; 2022: 21; 2023: 10; 2024: 7; 2025: 5.

63 papers.

Sort:

By area:

  1. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  2. 2023SATR: Zero-Shot Semantic Segmentation of 3D Shapescited by 62
  3. 2021Adaptive Graph Convolution for Point Cloud Analysiscited by 60
  4. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  5. 2021A Survey on Deep Domain Adaptation for LiDAR Perceptioncited by 46
  6. 2024Segment Any Meshcited by 37
  7. 2021PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoningcited by 34
  8. 2021BuildingNet: Learning to Label 3D Buildingscited by 33
  9. 2021Deep Learning Based 3D Segmentation: A Surveycited by 30
  10. 2024Query2CAD: Generating CAD models using natural language queriescited by 28
  11. 2023PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillationcited by 27
  12. 2021Voint Cloud: Multi-View Point Cloud Representation for 3D Understandingcited by 22
38 more
  1. 20223D Vision with Transformers: A Surveycited by 21
  2. 2022Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysiscited by 19
  3. 2021A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarioscited by 18
  4. 2022RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structurescited by 18
  5. 2025LitePT: Lighter Yet Stronger Point Transformercited by 17
  6. 2021Residual 3D Scene Flow Learning with Context-Aware Feature Extractioncited by 15
  7. 2023CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programscited by 15
  8. 2024Geometric Deep Learning for Computer-Aided Design: A Surveycited by 14
  9. 2024iSeg: Interactive 3D Segmentation via Interactive Attentioncited by 14
  10. 2022AGConv: Adaptive Graph Convolution on 3D Point Cloudscited by 13
  11. 2023Neural Semantic Surface Mapscited by 13
  12. 2022Laplacian2Mesh: Laplacian-Based Mesh Understandingcited by 11
  13. 2022MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentationcited by 10
  14. 2022SegNeRF: 3D Part Segmentation with Neural Radiance Fieldscited by 9
  15. 2022Semi-supervised 3D shape segmentation with multilevel consistency and part substitutioncited by 8
  16. 2023A Review of Panoptic Segmentation for Mobile Mapping Point Cloudscited by 8
  17. 2021Continuous Conditional Random Field Convolution for Point Cloud Segmentationcited by 7
  18. 2022MVTN: Learning Multi-View Transformations for 3D Understandingcited by 7
  19. 2022Neural Part Priors: Learning to Optimize Part-Based Object Completion in RGB-D Scanscited by 6
  20. 2022Unsupervised Domain Adaptation through Shape Modeling for Medical Image Segmentationcited by 6
  21. 2021HybridSDF: Combining Deep Implicit Shapes and Geometric Primitives for 3D Shape Representation and Manipulationcited by 5
  22. 2022Photo-to-Shape Material Transfer for Diverse Structurescited by 5
  23. 2023Test-Time Augmentation for 3D Point Cloud Classification and Segmentationcited by 4
  24. 2021Medial Spectral Coordinates for 3D Shape Analysiscited by 3
  25. 2023Multi-View Representation is What You Need for Point-Cloud Pre-Trainingcited by 3
  26. 2023MeT: A Graph Transformer for Semantic Segmentation of 3D Meshescited by 3
  27. 2024Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Surveycited by 3
  28. 2025Name That Part: 3D Part Segmentation and Namingcited by 3
  29. 2021CLOI: An Automated Benchmark Framework For Generating Geometric Digital Twins Of Industrial Facilitiescited by 2
  30. 2022Multi-scale Network with Attentional Multi-resolution Fusion for Point Cloud Semantic Segmentationcited by 2
  31. 2022Seg&Struct: The Interplay Between Part Segmentation and Structure Inference for 3D Shape Parsingcited by 2
  32. 2022Parsing Objects at a Finer Granularity: A Surveycited by 2
  33. 2021ActivationNet: Representation learning to predict contact quality of interacting 3-D surfaces in engineering designscited by 1
  34. 2021Learning 3D Mineral Prospectivity from 3D Geological Models Using Convolutional Neural Networks: Application to a Structure-controlled Hydrothermal Gold Depositcited by 1
  35. 2021iSeg3D: An Interactive 3D Shape Segmentation Toolcited by 1
  36. 2023Conformal Predictions Enhanced Expert-guided Meshing with Graph Neural Networkscited by 1
  37. 20233DFusion, A real-time 3D object reconstruction pipeline based on streamed instance segmented datacited by 1
  38. 2024Constraint-Aware Feature Learning for Parametric Point Cloudcited by 1

50 most cited of 63 All 63 (JSON)