mlsanityData to 14 Oct 2026

What Do Single-view 3D Reconstruction Networks Learn?

arXiv 1905.03678 ↗First posted 9 May 2019cs.CVcited by 260

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research. All existing techniques are united by the idea of having an encoder-decoder network that performs non-trivial reasoning about the 3D structure of the output space. In this work, we set up two alternative approaches that perform image classification and retrieval respectively. These simple baselines yield better results than state-of-the-art methods, both qualitatively and quantitatively. We show that encoder-decoder methods are statistically indistinguishable from these baselines, thus indicating that the current state of the art in single-view object reconstruction does not actually perform reconstruction but image classification. We identify aspects of popular experimental procedures that elicit this behavior and discuss ways to improve the current state of research.

Key facts. Cited by 260 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 51; 2022: 50; 2023: 61; 2024: 47; 2025: 31; 2026: 20.

260 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  2. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 645
  3. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 366
  4. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 306
  5. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 288
  6. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
  7. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  8. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 200
  9. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 197
  10. 2021CodeNeRF: Disentangled Neural Radiance Fields for Object Categoriescited by 183
  11. 2024Probing the 3D Awareness of Visual Foundation Modelscited by 177
  12. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 112
38 more
  1. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  2. 2021Variational Relational Point Completion Networkcited by 104
  3. 2021Unsupervised Discovery of Object Radiance Fieldscited by 101
  4. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completioncited by 100
  5. 20223DILG: Irregular Latent Grids for 3D Generative Modelingcited by 93
  6. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  7. 2022What's in your hands? 3D Reconstruction of Generic Objects in Handscited by 90
  8. 2023PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstructioncited by 84
  9. 2022SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformercited by 83
  10. 2023HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Videocited by 78
  11. 2023Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clipscited by 74
  12. 2023SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusioncited by 72
  13. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
  14. 2023AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformerscited by 67
  15. 2021Shelf-Supervised Mesh Prediction in the Wildcited by 65
  16. 2023Deep Learning on Implicit Neural Representations of Shapescited by 63
  17. 2021SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networkscited by 59
  18. 2021Neural Fields as Learnable Kernels for 3D Reconstructioncited by 58
  19. 2023PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigmcited by 56
  20. 2022Surface Reconstruction from Point Clouds by Learning Predictive Context Priorscited by 54
  21. 2023NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotationscited by 53
  22. 2021Multi-view 3D Reconstruction with Transformercited by 52
  23. 2024PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observationscited by 51
  24. 2021Neural Marching Cubescited by 50
  25. 2022Ponder: Point Cloud Pre-training via Neural Renderingcited by 50
  26. 2023gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstructioncited by 50
  27. 2022Vox-Surf: Voxel-based Implicit Surface Representationcited by 49
  28. 2023Reconstructing Animatable Categories from Videoscited by 47
  29. 2021View-Guided Point Cloud Completioncited by 46
  30. 2023Explicit Correspondence Matching for Generalizable Neural Radiance Fieldscited by 46
  31. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  32. 2024Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Modelscited by 44
  33. 2021Joint Learning of 3D Shape Retrieval and Deformationcited by 42
  34. 2022Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Imagecited by 42
  35. 2021Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Imagecited by 39
  36. 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
  37. 2023Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generationcited by 38
  38. 2024EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wildcited by 36

50 most cited of 260 All 260 (JSON)