mlsanityData to 14 Oct 2026

Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction

arXiv 1801.03910 ↗First posted 11 Jan 2018cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

We present a framework for learning single-view shape and pose prediction without using direct supervision for either. Our approach allows leveraging multi-view observations from unknown poses as supervisory signal during training. Our proposed training setup enforces geometric consistency between the independently predicted shape and pose from two views of the same instance. We consequently learn to predict shape in an emergent canonical (view-agnostic) frame along with a corresponding pose predictor. We show empirical and qualitative results using the ShapeNet dataset and observe encouragingly competitive performance to previous techniques which rely on stronger forms of supervision. We also demonstrate the applicability of our framework in a realistic setting which is beyond the scope of existing techniques: using a training dataset comprised of online product images where the underlying shape and pose are unknown.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 23; 2022: 11; 2023: 11; 2024: 3; 2025: 4.

52 papers.

Sort:

By area:

  1. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  2. 2021Unsupervised Learning of 3D Object Categories from Videos in the Wildcited by 67
  3. 2022Motion Inspired Unsupervised Perception and Prediction in Autonomous Drivingcited by 59
  4. 2021Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimationcited by 45
  5. 2021UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Renderingcited by 44
  6. 2021Learning Generative Models of Textured 3D Meshes from Real-World Imagescited by 44
  7. 2021SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Datacited by 38
  8. 2023LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFscited by 33
  9. 2021Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matchingcited by 26
  10. 2022Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstructioncited by 26
  11. 2022Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistencycited by 26
  12. 2022Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolationcited by 26
38 more
  1. 2021View Generalization for Single Image Textured 3D Modelscited by 19
  2. 2021Self-Supervised Point Cloud Completion via Inpaintingcited by 16
  3. 20213D-RETR: End-to-End Single and Multi-View 3D Reconstruction with Transformerscited by 15
  4. 2022Fine Detailed Texture Learning for 3D Meshes with Generative Modelscited by 15
  5. 2021Discovering 3D Parts from Image Collectionscited by 13
  6. 2022Towards Learning Neural Representations from Shadowscited by 12
  7. 20233D Reconstruction of Objects in Hands without Real World 3D Supervisioncited by 12
  8. 2023MV-DeepSDF: Implicit Modeling with Multi-Sweep Point Clouds for 3D Vehicle Reconstruction in Autonomous Drivingcited by 11
  9. 2023Progressive Learning of 3D Reconstruction Network from 2D GAN Datacited by 10
  10. 2021Mask-ToF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imagingcited by 9
  11. 2023Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updatescited by 9
  12. 2021Unsupervised Novel View Synthesis from a Single Imagecited by 8
  13. 2021Object Wake-up: 3D Object Rigging from a Single Imagecited by 8
  14. 2021An Effective Loss Function for Generating 3D Models from Single 2D Image without Renderingcited by 7
  15. 2021Lifting 2D Object Locations to 3D by Discounting LiDAR Outliers across Objects and Viewscited by 7
  16. 2025WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Explorationcited by 7
  17. 2022A Light Touch Approach to Teaching Transformers Multi-view Geometrycited by 6
  18. 2021Semi-supervised Viewpoint Estimation with Geometry-aware Conditional Generationcited by 5
  19. 2021Multi-Category Mesh Reconstruction From Image Collectionscited by 5
  20. 2022ViewNet: Unsupervised Viewpoint Estimation from Conditional Generationcited by 3
  21. 2023Attention-based Part Assembly for 3D Volumetric Shape Modelingcited by 3
  22. 2024TreeSBA: Tree-Transformer for Self-Supervised Sequential Brick Assemblycited by 3
  23. 2021STR-GQN: Scene Representation and Rendering for Unknown Cameras Based on Spatial Transformation Routingcited by 2
  24. 2021SSR: Semi-supervised Soft Rasterizer for single-view 2D to 3D Reconstructioncited by 2
  25. 20223D Cartoon Face Generation with Controllable Expressions from a Single GAN Imagecited by 2
  26. 2022ViewNeRF: Unsupervised Viewpoint Estimation Using Category-Level Neural Radiance Fieldscited by 2
  27. 2022Equivariant Light Field Convolution and Transformercited by 2
  28. 2023Self-Supervised Generative-Contrastive Learning of Multi-Modal Euclidean Input for 3D Shape Latent Representations: A Dynamic Switching Approachcited by 2
  29. 2023Self-supervised learning of object pose estimation using keypoint predictioncited by 1
  30. 2023Self-supervised Learning for Enhancing Geometrical Modeling in 3D-Aware Generative Adversarial Networkcited by 1
  31. 2021Centimeter-Wave Free-Space Time-of-Flight Imagingcited by 0
  32. 2021SE-MD: A Single-encoder multiple-decoder deep network for point cloud generation from 2D imagescited by 0
  33. 2021Learnable Triangulation for Deep Learning-based 3D Reconstruction of Objects of Arbitrary Topology from Single RGB Imagescited by 0
  34. 2023Are All Point Clouds Suitable for Completion? Weakly Supervised Quality Evaluation Network for Point Cloud Completioncited by 0
  35. 20233DMiner: Discovering Shapes from Large-Scale Unannotated Image Datasetscited by 0
  36. 2024Geometry aware 3D generation from in-the-wild images in ImageNetcited by 0
  37. 2024Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformerscited by 0
  38. 2025Glissando-Net: Deep sinGLe vIew category level poSe eStimation ANd 3D recOnstructioncited by 0

50 most cited of 52 All 52 (JSON)