mlsanityData to 7 Oct 2026

Semi-supervised Viewpoint Estimation with Geometry-aware Conditional Generation

arXiv 2104.01103 ↗First posted 2 Apr 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

There is a growing interest in developing computer vision methods that can learn from limited supervision. In this paper, we consider the problem of learning to predict camera viewpoints, where obtaining ground-truth annotations are expensive and require special equipment, from a limited number of labeled images. We propose a semi-supervised viewpoint estimation method that can learn to infer viewpoint information from unlabeled image pairs, where two images differ by a viewpoint change. In particular our method learns to synthesize the second image by combining the appearance from the first one and viewpoint from the second one. We demonstrate that our method significantly improves the supervised techniques, especially in the low-label regime and outperforms the state-of-the-art semi-supervised methods.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 36 of its 49 references that are in the map. First posted on arXiv 2 Apr 2021.

Builds on

36 of 49 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2015Fast R-CNNcited by 2,930
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  6. 2015Spatial Transformer Networkscited by 1,423
  7. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  8. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  9. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  10. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  11. 2018Spherical CNNscited by 452
  12. 2017Neural 3D Mesh Renderercited by 437
24 more
  1. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  2. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  3. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  4. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  5. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  6. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  7. 2015Deep Convolutional Inverse Graphics Networkcited by 121
  8. 2016Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervisioncited by 106
  9. 2015Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Viewscited by 94
  10. 2018Unsupervised Learning of Shape and Pose with Differentiable Point Cloudscited by 89
  11. 2018Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoningcited by 79
  12. 2018Unsupervised Geometry-Aware Representation for 3D Human Pose Estimationcited by 73
  13. 2017Unsupervised learning of object landmarks by factorized spatial embeddingscited by 64
  14. 2014Viewpoints and Keypointscited by 59
  15. 2019HoloGAN: Unsupervised learning of 3D representations from natural imagescited by 59
  16. 2018Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Predictioncited by 52
  17. 2018StarMap for Category-Agnostic Keypoint and Viewpoint Estimationcited by 42
  18. 2019Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spherescited by 37
  19. 2017Interpretable Transformations with Encoder-Decoder Networkscited by 33
  20. 20183D Pose Estimation and 3D Model Retrieval for Objects in the Wildcited by 31
  21. 2016Multiview RGB-D Dataset for Object Instance Detectioncited by 26
  22. 2020Self-Supervised Viewpoint Learning From Image Collectionscited by 23
  23. 2018Cross-Domain 3D Equivariant Image Embeddingscited by 12
  24. 2020Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimationcited by 7

Built on by

Cited by year

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

5 papers.

  1. 2023NOPE: Novel Object Pose Estimation from a Single Imagecited by 38
  2. 2022FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filteringcited by 16
  3. 20243D Equivariant Pose Regression via Direct Wigner-D Harmonics Predictioncited by 4
  4. 2022ViewNet: Unsupervised Viewpoint Estimation from Conditional Generationcited by 3
  5. 2022ViewNeRF: Unsupervised Viewpoint Estimation Using Category-Level Neural Radiance Fieldscited by 2