mlsanityData to 7 Oct 2026

PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning

arXiv 2105.05643 ↗First posted 12 May 2021cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

Motivated by the need for estimating the 3D pose of arbitrary objects, we consider the challenging problem of class-agnostic object viewpoint estimation from images only, without CAD model knowledge. The idea is to leverage features learned on seen classes to estimate the pose for classes that are unseen, yet that share similar geometries and canonical frames with seen classes. We train a direct pose estimator in a class-agnostic way by sharing weights across all object classes, and we introduce a contrastive learning method that has three main ingredients: (i) the use of pre-trained, self-supervised, contrast-based features; (ii) pose-aware data augmentations; (iii) a pose-aware contrastive loss. We experimented on Pascal3D+, ObjectNet3D and Pix3D in a cross-dataset fashion, with both seen and unseen classes. We report state-of-the-art results, including against methods that additionally use CAD models as input.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 65 of its 86 references that are in the map. First posted on arXiv 12 May 2021.

Builds on

65 of 86 references.

References · 65

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2017Mask R-CNNcited by 7,259
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  9. 2020Supervised Contrastive Learningcited by 2,803
  10. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  11. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  12. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
38 more
  1. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  2. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  3. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  4. 2019Contrastive Multiview Codingcited by 1,297
  5. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  6. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  7. 2016Colorful Image Colorizationcited by 1,113
  8. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  9. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
  10. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  11. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  12. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  13. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  14. 20163D Bounding Box Estimation Using Deep Learning and Geometrycited by 277
  15. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  16. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  17. 2020What Should Not Be Contrastive in Contrastive Learningcited by 224
  18. 2018Pix3D: Dataset and Methods for Single-Image 3D Shape Modelingcited by 218
  19. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  20. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  21. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  22. 2019Cross-Batch Memory for Embedding Learningcited by 130
  23. 2019Self-supervised 6D Object Pose Estimation for Robot Manipulationcited by 100
  24. 2015Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Viewscited by 94
  25. 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 88
  26. 2020Self6D: Self-Supervised Monocular 6D Object Pose Estimationcited by 79
  27. 2018Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimationcited by 74
  28. 2015Learning Descriptors for Object Recognition and 3D Pose Estimationcited by 60
  29. 2014Viewpoints and Keypointscited by 59
  30. 2018A Unified Framework for Multi-View Multi-Class Object Pose Estimationcited by 49
  31. 2018Deep Directional Statistics: Pose Estimation with Uncertainty Quantificationcited by 45
  32. 2018StarMap for Category-Agnostic Keypoint and Viewpoint Estimationcited by 42
  33. 2019Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objectscited by 39
  34. 2019Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spherescited by 37
  35. 2019On Object Symmetries and 6D Pose Estimation from Imagescited by 33
  36. 2018DenseReg: Fully Convolutional Dense Shape Regression In-the-Wildcited by 32
  37. 20183D Pose Estimation and 3D Model Retrieval for Objects in the Wildcited by 31
  38. 2020Self-Supervised Viewpoint Learning From Image Collectionscited by 23

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 8; 2023: 2; 2024: 2; 2025: 2; 2026: 3.

19 papers.

Sort:

  1. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
  2. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  3. 2022Zero-Shot Category-Level Object Pose Estimationcited by 57
  4. 2022Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusionscited by 54
  5. 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objectscited by 32
  6. 2021LARGE: Latent-Based Regression through GAN Semanticscited by 17
  7. 2022Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objectscited by 17
  8. 2021DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimationcited by 12
  9. 2023You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Examplecited by 8
  10. 2024Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videoscited by 5
  11. 2022Local Manifold Augmentation for Multiview Semantic Consistencycited by 3
  12. 20223D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimationcited by 2
7 more
  1. 2022Category-Level Pose Retrieval with Contrastive Features Learnt with Occlusion Augmentationcited by 2
  2. 2022Accidental Turntables: Learning 3D Pose by Watching Objects Turncited by 1
  3. 2025VOCAL: Visual Odometry via ContrAstive Learningcited by 0
  4. 2025Learning Point Cloud Representations with Pose Continuity for Depth-Based Category-Level 6D Object Pose Estimationcited by 0
  5. 2026HACMatch Semi-Supervised Rotation Regression with Hardness-Aware Curriculum Pseudo Labelingcited by 0
  6. 2026Every9D-21M: Large-Scale Real-World 9D Canonicalization of Everyday Objectscited by 0
  7. 2026Moving6DPoSe: A Multimodal Database for Monocular 6D Pose Estimation and Segmentation of Moving Objectscited by 0