mlsanityData to 7 Oct 2026

Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency

arXiv 1704.06254 ↗First posted 20 Apr 2017cs.CVcited by 177

Not on the map. Why?

Abstract (arXiv)

We study the notion of consistency between a 3D shape and a 2D observation and propose a differentiable formulation which allows computing gradients of the 3D shape given an observation from an arbitrary view. We do so by reformulating view consistency using a differentiable ray consistency (DRC) term. We show that this formulation can be incorporated in a learning framework to leverage different types of multi-view observations e.g. foreground masks, depth, color images, semantics etc. as supervision for learning single-view 3D prediction. We present empirical analysis of our technique in a controlled setting. We also show that this approach allows us to improve over existing techniques for single-view reconstruction of objects from the PASCAL VOC dataset.

Key facts. Cited by 177 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 57; 2022: 41; 2023: 38; 2024: 21; 2025: 16; 2026: 4.

177 papers.

Sort:

By area:

  1. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  2. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  3. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  4. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  5. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  6. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  7. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  8. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  9. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  10. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  11. 2021Advances in Neural Renderingcited by 365
  12. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
38 more
  1. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  2. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  3. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  4. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  5. 2021Neural Articulated Radiance Fieldcited by 196
  6. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 179
  7. 2022SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fieldscited by 144
  8. 2023NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidancecited by 137
  9. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
  10. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Datacited by 113
  11. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
  12. 2023Neural Kernel Surface Reconstructioncited by 102
  13. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  14. 2022ReLU Fields: The Little Non-linearity That Couldcited by 87
  15. 2021Unsupervised Learning of 3D Object Categories from Videos in the Wildcited by 67
  16. 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 66
  17. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstructioncited by 66
  18. 2021Shelf-Supervised Mesh Prediction in the Wildcited by 65
  19. 2023Texture Generation on 3D Meshes with Point-UV Diffusioncited by 63
  20. 2021CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assemblycited by 62
  21. 2021S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modelingcited by 59
  22. 2022Motion Inspired Unsupervised Perception and Prediction in Autonomous Drivingcited by 59
  23. 2021Neural Fields as Learnable Kernels for 3D Reconstructioncited by 58
  24. 2022Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulationcited by 57
  25. 2025Bolt3D: Generating 3D Scenes in Secondscited by 57
  26. 2021Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketchescited by 54
  27. 2022Few-View Object Reconstruction with Unknown Categories and Camera Posescited by 53
  28. 2024VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstructioncited by 50
  29. 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
  30. 2021Learning Generative Models of Textured 3D Meshes from Real-World Imagescited by 44
  31. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 41
  32. 2023Neural Volumetric Memory for Visual Locomotion Controlcited by 40
  33. 2023Reference-guided Controllable Inpainting of Neural Radiance Fieldscited by 40
  34. 2022LaTeRF: Label and Text Driven Object Radiance Fieldscited by 38
  35. 2023Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitivescited by 37
  36. 2024MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generationcited by 35
  37. 2021Active 3D Shape Reconstruction from Vision and Touchcited by 34
  38. 2021Video Autoencoder: self-supervised disentanglement of static 3D structure and motioncited by 34

50 most cited of 177 All 177 (JSON)