mlsanityData to 7 Oct 2026

Multi-view Convolutional Neural Networks for 3D Shape Recognition

arXiv 1505.00880 ↗First posted 5 May 2015cs.CV cs.GRcited by 564

Not on the map. Why?

Abstract (arXiv)

A longstanding question in computer vision concerns the representation of 3D shapes for recognition: should 3D shapes be represented with descriptors operating on their native 3D formats, such as voxel grid or polygon mesh, or can they be effectively represented with view-based descriptors? We address this question in the context of learning to recognize 3D shapes from a collection of their rendered views on 2D images. We first present a standard CNN architecture trained to recognize the shapes' rendered views independently of each other, and show that a 3D shape can be recognized even from a single view at an accuracy far higher than using state-of-the-art 3D shape descriptors. Recognition rates further increase when multiple views of the shapes are provided. In addition, we present a novel CNN architecture that combines information from multiple views of a 3D shape into a single and compact shape descriptor offering even better recognition performance. The same architecture can be applied to accurately recognize human hand-drawn sketches of shapes. We conclude that a collection of 2D views can be highly informative for 3D shape recognition and is amenable to emerging CNN architectures and their derivatives.

Key facts. Cited by 564 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 May 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 149; 2022: 114; 2023: 121; 2024: 85; 2025: 63; 2026: 32.

564 papers.

Sort:

By area:

  1. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  2. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  3. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  4. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  5. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  6. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  7. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  8. 2021Group-Free 3D Object Detection via Transformerscited by 215
  9. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  10. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 186
  11. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 175
  12. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
38 more
  1. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  2. 2022CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingcited by 159
  3. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  4. 2022Multi-View Transformer for 3D Visual Groundingcited by 138
  5. 2024RVT-2: Learning Precise Manipulation from Few Demonstrationscited by 135
  6. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 133
  7. 2021Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Predictioncited by 131
  8. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 124
  9. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 115
  10. 2021Improving 3D Object Detection with Channel-wise Transformercited by 108
  11. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 105
  12. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  13. 2022Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networkscited by 92
  14. 2022Learning to Generate Realistic LiDAR Point Cloudscited by 91
  15. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 85
  16. 2022Surface Representation for Point Cloudscited by 84
  17. 2023OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentationcited by 82
  18. 20213D Semantic Scene Completion: a Surveycited by 74
  19. 2022P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Promptingcited by 74
  20. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 74
  21. 2024MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistancecited by 72
  22. 2024Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategycited by 71
  23. 2023Learning Neural Volumetric Representations of Dynamic Humans in Minutescited by 70
  24. 2023ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidancecited by 70
  25. 2021Subdivision-Based Mesh Convolution Networkscited by 60
  26. 2021Adaptive Graph Convolution for Point Cloud Analysiscited by 60
  27. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  28. 2021Semantics for Robotic Mapping, Perception and Interaction: A Surveycited by 56
  29. 2021Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Cloudscited by 55
  30. 2023Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learningcited by 55
  31. 2023Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Featurescited by 55
  32. 2021SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Networkcited by 54
  33. 20213D Siamese Voxel-to-BEV Tracker for Sparse Point Cloudscited by 54
  34. 20214DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understandingcited by 54
  35. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  36. 2022LidarGait: Benchmarking 3D Gait Recognition with Point Cloudscited by 54
  37. 2021A Review of Location Encoding for GeoAI: Methods and Applicationscited by 53
  38. 2021Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysiscited by 47

50 most cited of 564 All 564 (JSON)