mlsanityData to 7 Oct 2026

Learning Category-Specific Mesh Reconstruction from Image Collections

arXiv 1803.07549 ↗First posted 20 Mar 2018cs.CVcited by 317

Not on the map. Why?

Abstract (arXiv)

We present a learning framework for recovering the 3D shape, camera, and texture of an object from a single image. The shape is represented as a deformable 3D mesh model of an object category where a shape is parameterized by a learned mean shape and per-instance predicted deformation. Our approach allows leveraging an annotated image collection for training, where the deformable model and the 3D prediction mechanism are learned without relying on ground-truth 3D or multi-view supervision. Our representation enables us to go beyond existing 3D prediction approaches by incorporating texture inference as prediction of an image in a canonical appearance space. Additionally, we show that semantic keypoints can be easily associated with the predicted shapes. We present qualitative and quantitative results of our approach on CUB and PASCAL3D datasets and show that we can learn to predict diverse shapes and textures across objects using only annotated image collections. The project website can be found at https://akanazawa.github.io/cmr/.

Key facts. Cited by 317 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 74; 2022: 84; 2023: 69; 2024: 47; 2025: 22; 2026: 21.

317 papers.

Sort:

By area:

  1. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  2. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  3. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  4. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  5. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  6. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  7. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 395
  8. 2021Advances in Neural Renderingcited by 365
  9. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  10. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  11. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 199
  12. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 198
38 more
  1. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  2. 2021Probabilistic Modeling for Human Mesh Recoverycited by 152
  3. 2022StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learningcited by 140
  4. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
  5. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  6. 2022Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatarscited by 124
  7. 2024Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collectionscited by 117
  8. 2021LASR: Learning Articulated Shape Reconstruction from a Monocular Videocited by 115
  9. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Datacited by 113
  10. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervisioncited by 112
  11. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 111
  12. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 111
  13. 2023HoloDiffusion: Training a 3D Diffusion Model using 2D Imagescited by 106
  14. 2021Neural Lumigraph Renderingcited by 105
  15. 2021Stylizing 3D Scene via Implicit Representation and HyperNetworkcited by 103
  16. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  17. 2021NeuTex: Neural Texture Mapping for Volumetric Neural Renderingcited by 98
  18. 2023TextDeformer: Geometry Manipulation using Text Guidancecited by 94
  19. 2022POCO: Point Convolution for Surface Reconstructioncited by 91
  20. 2022What's in your hands? 3D Reconstruction of Generic Objects in Handscited by 90
  21. 2021H3D-Net: Few-Shot High-Fidelity 3D Head Reconstructioncited by 81
  22. 2023StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fieldscited by 79
  23. 2022Deforming Radiance Fields with Cagescited by 78
  24. 2021GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Drivingcited by 75
  25. 2025RayZer: A Self-supervised Large View Synthesis Modelcited by 74
  26. 2021A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesiscited by 72
  27. 2023Free3D: Consistent Novel View Synthesis without 3D Representationcited by 72
  28. 2023Multiview Compressive Coding for 3D Reconstructioncited by 71
  29. 2021Unsupervised Learning of 3D Object Categories from Videos in the Wildcited by 67
  30. 2024Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materialscited by 66
  31. 2021Shelf-Supervised Mesh Prediction in the Wildcited by 65
  32. 2022High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimizationcited by 65
  33. 2021DOVE: Learning Deformable 3D Objects by Watching Videoscited by 61
  34. 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
  35. 2022AutoRF: Learning 3D Object Radiance Fields from Single View Observationscited by 59
  36. 2022Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Datasetcited by 59
  37. 2024Learning the 3D Fauna of the Webcited by 58
  38. 2021Unsupervised Part Discovery from Contrastive Reconstructioncited by 57

50 most cited of 317 All 317 (JSON)