mlsanityData to 14 Oct 2026

Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild

arXiv 1911.11130 ↗First posted 25 Nov 2019cs.CVcited by 180

Not on the map. Why?

Abstract (arXiv)

We propose a method to learn 3D deformable object categories from raw single-view images, without external supervision. The method is based on an autoencoder that factors each input image into depth, albedo, viewpoint and illumination. In order to disentangle these components without supervision, we use the fact that many object categories have, at least in principle, a symmetric structure. We show that reasoning about illumination allows us to exploit the underlying object symmetry even if the appearance is not symmetric due to shading. Furthermore, we model objects that are probably, but not certainly, symmetric by predicting a symmetry probability map, learned end-to-end with the other components of the model. Our experiments show that this method can recover very accurately the 3D shape of human faces, cat faces and cars from single-view images, without any supervision or a prior shape model. On benchmarks, we demonstrate superior accuracy compared to another method that uses supervision at the level of 2D image correspondences.

Key facts. Cited by 180 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 57; 2022: 45; 2023: 48; 2024: 17; 2025: 8; 2026: 5.

180 papers.

Sort:

By area:

  1. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  2. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 397
  3. 2021GAN Inversion: A Surveycited by 367
  4. 2022EMOCA: Emotion Driven Monocular Face Capture and Animationcited by 255
  5. 2023Visual Geometry Grounded Deep Structure From Motioncited by 227
  6. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 199
  7. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  8. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 147
  9. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 112
  10. 2023HoloDiffusion: Training a 3D Diffusion Model using 2D Imagescited by 106
  11. 2022Vision Transformer for NeRF-Based View Synthesis from a Single Input Imagecited by 104
  12. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
38 more
  1. 2021LOLNeRF: Learn from One Lookcited by 84
  2. 2024SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesiscited by 84
  3. 2023EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimationcited by 79
  4. 2022Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields Translationcited by 73
  5. 2021A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesiscited by 72
  6. 2023Multiview Compressive Coding for 3D Reconstructioncited by 71
  7. 2021Unsupervised Learning of 3D Object Categories from Videos in the Wildcited by 67
  8. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstructioncited by 67
  9. 2024Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materialscited by 66
  10. 2021Shelf-Supervised Mesh Prediction in the Wildcited by 65
  11. 2021Model-based 3D Hand Reconstruction via Self-Supervised Learningcited by 65
  12. 2023Behind the Scenes: Density Fields for Single View Reconstructioncited by 63
  13. 2021DOVE: Learning Deformable 3D Objects by Watching Videoscited by 61
  14. 2022AutoRF: Learning 3D Object Radiance Fields from Single View Observationscited by 59
  15. 2022StyleLight: HDR Panorama Generation for Lighting Estimation and Editingcited by 59
  16. 2024Learning the 3D Fauna of the Webcited by 59
  17. 2021SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimationcited by 53
  18. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  19. 2021DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderercited by 52
  20. 2021Generative Occupancy Fields for 3D Surface-Aware Image Synthesiscited by 51
  21. 2021Reconstructing 3D Human Pose by Watching Humans in the Mirrorcited by 47
  22. 2021FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modellingcited by 47
  23. 2021Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGANcited by 45
  24. 2023Learning Disentangled Avatars with Hybrid 3D Representationscited by 44
  25. 2022Neural Radiance Transfer Fields for Relightable Novel-view Synthesis with Global Illuminationcited by 41
  26. 2023TriPlaneNet: An Encoder for EG3D Inversioncited by 41
  27. 2022AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesiscited by 39
  28. 20223D GAN Inversion with Facial Symmetry Priorcited by 39
  29. 2023Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusioncited by 38
  30. 2022REALY: Rethinking the Evaluation of 3D Face Reconstructioncited by 33
  31. 2023LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFscited by 33
  32. 2023HoloFusion: Towards Photo-realistic 3D Generative Modelingcited by 32
  33. 2022De-rendering 3D Objects in the Wildcited by 31
  34. 2022State of the Art in Dense Monocular Non-Rigid 3D Reconstructioncited by 30
  35. 2021De-rendering the World's Revolutionary Artefactscited by 28
  36. 2022Consistent 3D Hand Reconstruction in Video via self-supervised Learningcited by 28
  37. 2023Material Palette: Extraction of Materials from a Single Imagecited by 28
  38. 2023HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3Dcited by 28

50 most cited of 180 All 180 (JSON)