mlsanityData to 14 Oct 2026

Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Views

arXiv 2108.03743 ↗First posted 8 Aug 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Unsupervised learning of global features for 3D shape analysis is an important research challenge because it avoids manual effort for supervised information collection. In this paper, we propose a view-based deep learning model called Hierarchical View Predictor (HVP) to learn 3D shape features from unordered views in an unsupervised manner. To mine highly discriminative information from unordered views, HVP performs a novel hierarchical view prediction over a view pair, and aggregates the knowledge learned from the predictions in all view pairs into a global feature. In a view pair, we pose hierarchical view prediction as the task of hierarchically predicting a set of image patches in a current view from its complementary set of patches, and in addition, completing the current view and its opposite from any one of the two sets of patches. Hierarchical prediction, in patches to patches, patches to view and view to view, facilitates HVP to effectively learn the structure of 3D shapes from the correlation between patches in the same view and the correlation between a pair of complementary views. In addition, the employed implicit aggregation over all view pairs enables HVP to learn global features from unordered views. Our results show that HVP can outperform state-of-the-art methods under large-scale 3D shape benchmarks in shape classification and retrieval.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 47 of its 76 references that are in the map. First posted on arXiv 8 Aug 2021.

Builds on

47 of 76 references.

References · 47

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  4. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  5. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  6. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  7. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  8. 2015DeepStereo: Learning to Predict New Views from the World's Imagerycited by 185
  9. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  10. 2016View Synthesis by Appearance Flowcited by 172
  11. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  12. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 147
35 more
  1. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  2. 2016Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervisioncited by 106
  3. 20183D Point Capsule Networkscited by 106
  4. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  5. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  6. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100
  7. 2020PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Pathscited by 97
  8. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  9. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  10. 2018Point Cloud GANcited by 79
  11. 2020Self-supervised Learning of Point Clouds via Orientation Estimationcited by 72
  12. 2018Triplet-Center Loss for Multi-View 3D Object Retrievalcited by 69
  13. 2016Unsupervised Learning of 3D Structure from Imagescited by 67
  14. 2019Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Predictioncited by 66
  15. 2018Learning Descriptor Networks for 3D Shape Synthesis and Analysiscited by 56
  16. 2021Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learningcited by 52
  17. 2016VConv-DAE: Deep Volumetric Shape Learning Without Object Labelscited by 50
  18. 2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
  19. 2018View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictionscited by 43
  20. 2020DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Imagescited by 35
  21. 2019L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attentioncited by 32
  22. 2020Fine-Grained 3D Shape Classification with Hierarchical Part-View Attentionscited by 30
  23. 2018Y^2Seq2Seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequencescited by 27
  24. 2019Dominant Set Clustering and Pooling for Multi-View 3D Object Recognitioncited by 25
  25. 2019GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformationscited by 22
  26. 20193D Shape Completion with Multi-view Consistent Inferencecited by 22
  27. 2016Orientation-boosted Voxel Nets for 3D Object Recognitioncited by 17
  28. 2020SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinatescited by 17
  29. 2016Pairwise Decomposition of Image Sequences for Active Multi-View Recognitioncited by 15
  30. 2019Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsulescited by 14
  31. 2015Unsupervised Learning of Visual Structure using Predictive Generative Networkscited by 12
  32. 20193DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attentioncited by 12
  33. 2019Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Viewscited by 10
  34. 2020LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contextscited by 10
  35. 2019NeuralSampler: Euclidean Point Cloud Auto-Encoder and Samplercited by 4

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 1; 2024: 2.

7 papers.

  1. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 164
  2. 2022Learning Deep Implicit Functions for 3D Shapes with Dynamic Code Cloudscited by 42
  3. 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
  4. 2022Fast Learning Radiance Fields by Shooting Much Fewer Rayscited by 38
  5. 2023Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priorscited by 28
  6. 2024HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillationcited by 11
  7. 2024Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priorscited by 7