mlsanityData to 14 Oct 2026

View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions

arXiv 1811.02744 ↗First posted 7 Nov 2018cs.CVcited by 43

Not on the map. Why?

Abstract (arXiv)

In this paper we present a novel unsupervised representation learning approach for 3D shapes, which is an important research challenge as it avoids the manual effort required for collecting supervised data. Our method trains an RNN-based neural network architecture to solve multiple view inter-prediction tasks for each shape. Given several nearby views of a shape, we define view inter-prediction as the task of predicting the center view between the input views, and reconstructing the input views in a low-level feature space. The key idea of our approach is to implement the shape representation as a shape-specific global memory that is shared between all local view inter-predictions for each shape. Intuitively, this memory enables the system to aggregate information that is useful to better solve the view inter-prediction tasks for each shape, and to leverage the memory as a view-independent shape representation. Our approach obtains the best results using a combination of L_2 and adversarial losses for the view inter-prediction task. We show that VIP-GAN outperforms state-of-the-art methods in unsupervised 3D feature learning on three large scale 3D shape benchmarks.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 19; 2023: 7; 2024: 5; 2025: 2.

43 papers.

Sort:

By area:

  1. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 264
  2. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  3. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  4. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 164
  5. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 144
  6. 2022Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priorscited by 60
  7. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  8. 2022Surface Reconstruction from Point Clouds by Learning Predictive Context Priorscited by 54
  9. 2023Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-trainingcited by 52
  10. 2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
  11. 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
  12. 2022Masked Autoencoders in 3D Point Cloud Representation Learningcited by 30
31 more
  1. 2021Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matchingcited by 26
  2. 2022Latent Partition Implicit with Surface Codes for 3D Representationcited by 21
  3. 2022Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learningcited by 19
  4. 20223D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Cloudscited by 18
  5. 2022POS-BERT: Point Cloud One-Stage BERT Pre-Trainingcited by 16
  6. 2024HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillationcited by 11
  7. 2022PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognitioncited by 10
  8. 2023ViPFormer: Efficient Vision-and-Pointcloud Transformer for Unsupervised Pointcloud Understandingcited by 8
  9. 2021Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Viewscited by 7
  10. 2021Representing Shape Collections with Alignment-Aware Linear Modelscited by 7
  11. 2022PointVST: Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translationcited by 7
  12. 2022Lifelong Ensemble Learning based on Multiple Representations for Few-Shot Object Recognitioncited by 6
  13. 2022SoftPool++: An Encoder-Decoder Network for Point Cloud Completioncited by 6
  14. 2024DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learningcited by 6
  15. 2021Point Discriminative Learning for Data-efficient 3D Point Cloud Analysiscited by 5
  16. 2022PointCMC: Cross-Modal Multi-Scale Correspondences Learning for Point Cloud Understandingcited by 5
  17. 2021Staying in Shape: Learning Invariant Shape Representations using Contrastive Learningcited by 4
  18. 2022Joint Data and Feature Augmentation for Self-Supervised Representation Learning on Point Cloudscited by 2
  19. 2023PointSmile: Point Self-supervised Learning via Curriculum Mutual Informationcited by 2
  20. 2021Points2Vec: Unsupervised Object-level Feature Learning from Point Cloudscited by 1
  21. 2021Unsupervised Contrastive Learning with Simple Transformation for 3D Point Cloud Datacited by 1
  22. 2022SPCNet: Stepwise Point Cloud Completion Networkcited by 1
  23. 2023CLR-GAM: Contrastive Point Cloud Learning with Guided Augmentation and Feature Mappingcited by 1
  24. 2023Cross-BERT for Point Cloud Pretrainingcited by 1
  25. 2024Triple Point Maskingcited by 1
  26. 2024Pic@Point: Cross-Modal Learning by Local and Global Point-Picture Correspondencecited by 1
  27. 2025A Cross Branch Fusion-Based Contrastive Learning Framework for Point Cloud Self-supervised Learningcited by 1
  28. 2023Evaluating 3D Shape Analysis Methods for Robustness to Rotation Invariancecited by 0
  29. 2023Self-supervised adversarial masking for 3D point cloud representation learningcited by 0
  30. 2024Masked Generative Extractor for Synergistic Representation and 3D Generation of Point Cloudscited by 0
  31. 2025LiLa-Net: Lightweight Latent LiDAR Autoencoder for 3D Point Cloud Reconstructioncited by 0