mlsanityData to 7 Oct 2026

Articulation-aware Canonical Surface Mapping

arXiv 2004.00614 ↗First posted 1 Apr 2020cs.CVcited by 80

Not on the map. Why?

Abstract (arXiv)

We tackle the tasks of: 1) predicting a Canonical Surface Mapping (CSM) that indicates the mapping from 2D pixels to corresponding points on a canonical template shape, and 2) inferring the articulation and pose of the template corresponding to the input image. While previous approaches rely on keypoint supervision for learning, we present an approach that can learn without such annotations. Our key insight is that these tasks are geometrically related, and we can obtain supervisory signal via enforcing consistency among the predictions. We present results across a diverse set of animal object categories, showing that our method can learn articulation and CSM prediction from image collections using only foreground mask labels for training. We empirically show that allowing articulation helps learn more accurate CSM prediction, and that enforcing the consistency with predicted CSM is similarly critical for learning meaningful articulation.

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 14; 2023: 18; 2024: 12; 2025: 6; 2026: 5.

80 papers.

Sort:

By area:

  1. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  2. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  3. 2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondencecited by 211
  4. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 199
  5. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  6. 2021LASR: Learning Articulated Shape Reconstruction from a Monocular Videocited by 115
  7. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 113
  8. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 111
  9. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  10. 2023Multiview Compressive Coding for 3D Reconstructioncited by 71
  11. 2021Unsupervised Learning of 3D Object Categories from Videos in the Wildcited by 67
  12. 2021Shelf-Supervised Mesh Prediction in the Wildcited by 65
38 more
  1. 2022LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discoverycited by 65
  2. 2021DOVE: Learning Deformable 3D Objects by Watching Videoscited by 61
  3. 2021GAN-Supervised Dense Visual Alignmentcited by 61
  4. 2024Learning the 3D Fauna of the Webcited by 58
  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. 2023Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shapecited by 43
  8. 2023Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusioncited by 37
  9. 2022Understanding 3D Object Articulation in Internet Videoscited by 36
  10. 2022CASA: Category-agnostic Skeletal Animal Reconstructioncited by 35
  11. 2022State of the Art in Dense Monocular Non-Rigid 3D Reconstructioncited by 30
  12. 2022Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemblecited by 30
  13. 2021Differentiable Stereopsis: Meshes from multiple views using differentiable renderingcited by 26
  14. 2022Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstructioncited by 26
  15. 2023ASIC: Aligning Sparse in-the-wild Image Collectionscited by 26
  16. 2024Real3D: Scaling Up Large Reconstruction Models with Real-World Imagescited by 24
  17. 2022Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wildcited by 22
  18. 2023ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collectionscited by 22
  19. 2021To The Point: Correspondence-driven monocular 3D category reconstructioncited by 21
  20. 2022Neural Correspondence Field for Object Pose Estimationcited by 21
  21. 2023Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videoscited by 21
  22. 2022Learning 3D Object Shape and Layout without 3D Supervisioncited by 19
  23. 2021Learning monocular 3D reconstruction of articulated categories from motioncited by 18
  24. 2023OmniMotionGPT: Animal Motion Generation with Limited Datacited by 18
  25. 2021Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstructioncited by 16
  26. 2024LEIA: Latent View-invariant Embeddings for Implicit 3D Articulationcited by 16
  27. 2023SAOR: Single-View Articulated Object Reconstructioncited by 15
  28. 2024Survey on Modeling of Human-made Articulated Objectscited by 14
  29. 2021Discovering Relationships between Object Categories via Universal Canonical Mapscited by 13
  30. 2023MoDA: Modeling Deformable 3D Objects from Casual Videoscited by 13
  31. 2025Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fieldscited by 13
  32. 2025Detection Based Part-level Articulated Object Reconstruction from Single RGBD Imagecited by 13
  33. 2021Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objectscited by 12
  34. 2023DreaMo: Articulated 3D Reconstruction From A Single Casual Videocited by 12
  35. 20222D GANs Meet Unsupervised Single-view 3D Reconstructioncited by 11
  36. 2024S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Videocited by 11
  37. 2024SHIC: Shape-Image Correspondences with no Keypoint Supervisioncited by 11
  38. 2023CAMM: Building Category-Agnostic and Animatable 3D Models from Monocular Videoscited by 10

50 most cited of 80 All 80 (JSON)