mlsanityData to 7 Oct 2026

C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion

arXiv 1909.02533 ↗First posted 5 Sep 2019cs.CV cs.GRcited by 60

Not on the map. Why?

Abstract (arXiv)

We propose C3DPO, a method for extracting 3D models of deformable objects from 2D keypoint annotations in unconstrained images. We do so by learning a deep network that reconstructs a 3D object from a single view at a time, accounting for partial occlusions, and explicitly factoring the effects of viewpoint changes and object deformations. In order to achieve this factorization, we introduce a novel regularization technique. We first show that the factorization is successful if, and only if, there exists a certain canonicalization function of the reconstructed shapes. Then, we learn the canonicalization function together with the reconstruction one, which constrains the result to be consistent. We demonstrate state-of-the-art reconstruction results for methods that do not use ground-truth 3D supervision for a number of benchmarks, including Up3D and PASCAL3D+. Source code has been made available at https://github.com/facebookresearch/c3dpo_nrsfm.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 18; 2023: 8; 2024: 4; 2025: 9; 2026: 3.

60 papers.

Sort:

By area:

  1. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  2. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 274
  3. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 247
  4. 2022Particle Video Revisited: Tracking Through Occlusions Using Point Trajectoriescited by 215
  5. 2021LASR: Learning Articulated Shape Reconstruction from a Monocular Videocited by 115
  6. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  7. 2025St4RTrack: Simultaneous 4D Reconstruction and Tracking in the Worldcited by 88
  8. 2023Multiview Compressive Coding for 3D Reconstructioncited by 71
  9. 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
  10. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  11. 2021Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objectscited by 50
  12. 2022Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervisioncited by 33
38 more
  1. 2022ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapescited by 31
  2. 2021Gravity-Aware Monocular 3D Human-Object Reconstructioncited by 30
  3. 2022State of the Art in Dense Monocular Non-Rigid 3D Reconstructioncited by 30
  4. 2021KAMA: 3D Keypoint Aware Body Mesh Articulationcited by 27
  5. 2022Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimationcited by 25
  6. 2022Unbiased 4D: Monocular 4D Reconstruction with a Neural Deformation Modelcited by 25
  7. 2022φ-SfT: Shape-from-Template with a Physics-Based Deformation Modelcited by 23
  8. 2021To The Point: Correspondence-driven monocular 3D category reconstructioncited by 21
  9. 2022Learning 3D Object Shape and Layout without 3D Supervisioncited by 19
  10. 2022Shape-Pose Disentanglement using SE(3)-equivariant Vector Neuronscited by 16
  11. 2021StrobeNet: Category-Level Multiview Reconstruction of Articulated Objectscited by 14
  12. 2024Fast Encoder-Based 3D from Casual Videos via Point Track Processingcited by 14
  13. 2021Discovering Relationships between Object Categories via Universal Canonical Mapscited by 13
  14. 2021MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networkscited by 13
  15. 2021Self-Supervised 3D Human Pose Estimation with Multiple-View Geometrycited by 10
  16. 2021PAUL: Procrustean Autoencoder for Unsupervised Liftingcited by 9
  17. 2021PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motioncited by 9
  18. 2022Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fieldscited by 9
  19. 2022Deep Non-rigid Structure-from-Motion: A Sequence-to-Sequence Translation Perspectivecited by 8
  20. 20233D-LFM: Lifting Foundation Modelcited by 8
  21. 2025Dynamic Scene Reconstruction: Recent Advance in Real-time Rendering and Streamingcited by 8
  22. 2022MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Viewscited by 7
  23. 2023Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modelingcited by 7
  24. 2022Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimationcited by 6
  25. 2021DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimensioncited by 5
  26. 2022Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstructioncited by 5
  27. 2022Category-Level Global Camera Pose Estimation with Multi-Hypothesis Point Cloud Correspondencescited by 3
  28. 2023Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learningcited by 3
  29. 2025Ev4DGS: Novel-view Rendering of Non-Rigid Objects from Monocular Event Streamscited by 3
  30. 2021GTT-Net: Learned Generalized Trajectory Triangulationcited by 2
  31. 2021High Fidelity 3D Reconstructions with Limited Physical Viewscited by 2
  32. 20233D Surface Reconstruction in the Wild by Deforming Shape Priors from Synthetic Datacited by 2
  33. 2026Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstructioncited by 2
  34. 2021Semi-supervised 3D Hand-Object Pose Estimation via Pose Dictionary Learningcited by 1
  35. 2021Pose Recognition in the Wild: Animal pose estimation using Agglomerative Clustering and Contrastive Learningcited by 1
  36. 2021End-to-End Learning of Multi-category 3D Pose and Shape Estimationcited by 1
  37. 2025Non-Rigid Structure-from-Motion via Differential Geometry with Recoverable Conformal Scalecited by 1
  38. 2025Inferring Compositional 4D Scenes without Ever Seeing Onecited by 1

50 most cited of 60 All 60 (JSON)