mlsanityData to 7 Oct 2026

Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network

arXiv 2208.00183 ↗First posted 30 Jul 2022cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

3D reconstruction of novel categories based on few-shot learning is appealing in real-world applications and attracts increasing research interests. Previous approaches mainly focus on how to design shape prior models for different categories. Their performance on unseen categories is not very competitive. In this paper, we present a Memory Prior Contrastive Network (MPCN) that can store shape prior knowledge in a few-shot learning based 3D reconstruction framework. With the shape memory, a multi-head attention module is proposed to capture different parts of a candidate shape prior and fuse these parts together to guide 3D reconstruction of novel categories. Besides, we introduce a 3D-aware contrastive learning method, which can not only complement the retrieval accuracy of memory network, but also better organize image features for downstream tasks. Compared with previous few-shot 3D reconstruction methods, MPCN can handle the inter-class variability without category annotations. Experimental results on a benchmark synthetic dataset and the Pascal3D+ real-world dataset show that our model outperforms the current state-of-the-art methods significantly.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 38 of its 50 references that are in the map. First posted on arXiv 30 Jul 2022.

Builds on

38 of 50 references.

References · 38

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2016Layer Normalizationcited by 5,579
  8. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  9. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  10. 2020Supervised Contrastive Learningcited by 2,803
  11. 2016Matching Networks for One Shot Learningcited by 2,246
  12. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
26 more
  1. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  2. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
  3. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  4. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  5. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  6. 2016Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Agecited by 405
  7. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  8. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  9. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
  10. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  11. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  12. 2017MarrNet: 3D Shape Reconstruction via 2.5D Sketchescited by 108
  13. 2019Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformationcited by 103
  14. 2020Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Imagescited by 79
  15. 2018Learning Shape Priors for Single-View 3D Completion and Reconstructioncited by 68
  16. 2017Learning to Remember Rare Eventscited by 63
  17. 2019Few-Shot Learning with Embedded Class Models and Shot-Free Meta Trainingcited by 57
  18. 2018Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layerscited by 33
  19. 2021Few-shot Open-set Recognition by Transformation Consistencycited by 29
  20. 2019Adaptive Posterior Learning: few-shot learning with a surprise-based memory modulecited by 25
  21. 2019Few-Shot Generalization for Single-Image 3D Reconstruction via Priorscited by 25
  22. 2019Knowledge Graph Transfer Network for Few-Shot Recognitioncited by 20
  23. 2018MVPNet: Multi-View Point Regression Networks for 3D Object Reconstruction from A Single Imagecited by 17
  24. 2020Few-Shot Single-View 3-D Object Reconstruction with Compositional Priorscited by 10
  25. 2017Structured Set Matching Networks for One-Shot Part Labelingcited by 6
  26. 2021Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstructioncited by 5

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 5; 2024: 2.

9 papers.

  1. 2023SimDA: Simple Diffusion Adapter for Efficient Video Generationcited by 101
  2. 2022SVFormer: Semi-supervised Video Transformer for Action Recognitioncited by 67
  3. 2023VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Modelscited by 19
  4. 2023PanoSwin: a Pano-style Swin Transformer for Panorama Understandingcited by 18
  5. 2024GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstructioncited by 18
  6. 2022GARNet: Global-Aware Multi-View 3D Reconstruction Network and the Cost-Performance Tradeoffcited by 8
  7. 2023UMIFormer: Mining the Correlations between Similar Tokens for Multi-View 3D Reconstructioncited by 7
  8. 2023A Fusion of Variational Distribution Priors and Saliency Map Replay for Continual 3D Reconstructioncited by 0
  9. 2024Shape2.5D: A Dataset of Texture-less Surfaces for Depth and Normals Estimationcited by 0