mlsanityData to 7 Oct 2026

3D Photography using Context-aware Layered Depth Inpainting

arXiv 2004.04727 ↗First posted 9 Apr 2020cs.CV eess.IVcited by 206

Not on the map. Why?

Cited by 26 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose a method for converting a single RGB-D input image into a 3D photo - a multi-layer representation for novel view synthesis that contains hallucinated color and depth structures in regions occluded in the original view. We use a Layered Depth Image with explicit pixel connectivity as underlying representation, and present a learning-based inpainting model that synthesizes new local color-and-depth content into the occluded region in a spatial context-aware manner. The resulting 3D photos can be efficiently rendered with motion parallax using standard graphics engines. We validate the effectiveness of our method on a wide range of challenging everyday scenes and show fewer artifacts compared with the state of the arts.

Key facts. Cited by 206 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 37; 2022: 39; 2023: 54; 2024: 42; 2025: 23; 2026: 11.

206 papers.

Sort:

By area:

  1. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  2. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  3. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  4. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  5. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  6. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 392
  7. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 341
  8. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 283
  9. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  10. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 197
  11. 2023Robust Dynamic Radiance Fieldscited by 193
  12. 2022SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Imagecited by 165
38 more
  1. 2021Efficient Neural Radiance Fields for Interactive Free-viewpoint Videocited by 150
  2. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Viewscited by 148
  3. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  4. 2023Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fieldscited by 122
  5. 2021SMD-Nets: Stereo Mixture Density Networkscited by 118
  6. 2023F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectoriescited by 118
  7. 2021Pathdreamer: A World Model for Indoor Navigationcited by 117
  8. 2023Consistent View Synthesis with Pose-Guided Diffusion Modelscited by 117
  9. 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimationcited by 116
  10. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  11. 2022Vision Transformer for NeRF-Based View Synthesis from a Single Input Imagecited by 104
  12. 2021Geometry-Free View Synthesis: Transformers and no 3D Priorscited by 99
  13. 2021NeRF-SR: High-Quality Neural Radiance Fields using Supersamplingcited by 95
  14. 2023Generative Image Dynamicscited by 93
  15. 20234K4D: Real-Time 4D View Synthesis at 4K Resolutioncited by 91
  16. 2021Neural Trajectory Fields for Dynamic Novel View Synthesiscited by 85
  17. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  18. 2022InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Imagescited by 82
  19. 2021Learning to Stylize Novel Viewscited by 76
  20. 2023TaleCrafter: Interactive Story Visualization with Multiple Characterscited by 71
  21. 2022Removing Objects From Neural Radiance Fieldscited by 66
  22. 2024Advances in 3D Generation: A Surveycited by 62
  23. 2024World-consistent Video Diffusion with Explicit 3D Modelingcited by 62
  24. 2021360MonoDepth: High-Resolution 360deg Monocular Depth Estimationcited by 60
  25. 2022Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Imagescited by 59
  26. 2023Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3Dcited by 59
  27. 2023Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenescited by 55
  28. 2024InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Priorcited by 55
  29. 2024LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generationcited by 53
  30. 2022DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Modelscited by 51
  31. 2024AGG: Amortized Generative 3D Gaussians for Single Image to 3Dcited by 51
  32. 2024GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Meshcited by 51
  33. 2021Learning Neural Light Fields with Ray-Space Embedding Networkscited by 49
  34. 2022SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstructioncited by 49
  35. 2021SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpaintingcited by 48
  36. 20233D generation on ImageNetcited by 47
  37. 20213D Photo Stylization: Learning to Generate Stylized Novel Views from a Single Imagecited by 45
  38. 2023PERF: Panoramic Neural Radiance Field from a Single Panoramacited by 45

50 most cited of 206 All 206 (JSON)