mlsanityData to 7 Oct 2026

Stereo Magnification: Learning View Synthesis using Multiplane Images

arXiv 1805.09817 ↗First posted 24 May 2018cs.CV cs.GRcited by 206

Not on the map. Why?

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

Abstract (arXiv)

The view synthesis problem--generating novel views of a scene from known imagery--has garnered recent attention due in part to compelling applications in virtual and augmented reality. In this paper, we explore an intriguing scenario for view synthesis: extrapolating views from imagery captured by narrow-baseline stereo cameras, including VR cameras and now-widespread dual-lens camera phones. We call this problem stereo magnification, and propose a learning framework that leverages a new layered representation that we call multiplane images (MPIs). Our method also uses a massive new data source for learning view extrapolation: online videos on YouTube. Using data mined from such videos, we train a deep network that predicts an MPI from an input stereo image pair. This inferred MPI can then be used to synthesize a range of novel views of the scene, including views that extrapolate significantly beyond the input baseline. We show that our method compares favorably with several recent view synthesis methods, and demonstrate applications in magnifying narrow-baseline stereo images.

Key facts. Cited by 206 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 44; 2022: 44; 2023: 39; 2024: 30; 2025: 34; 2026: 15.

206 papers.

Sort:

By area:

  1. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  2. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  3. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  4. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  5. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  6. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  7. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  8. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 356
  9. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 317
  10. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
  11. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
  12. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
38 more
  1. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  2. 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
  3. 2024A Survey on 3D Gaussian Splattingcited by 221
  4. 2023BakedSDF: Meshing Neural SDFs for Real-Time View Synthesiscited by 220
  5. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  6. 2022NeRF-Editing: Geometry Editing of Neural Radiance Fieldscited by 216
  7. 2021NeX: Real-time View Synthesis with Neural Basis Expansioncited by 215
  8. 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 215
  9. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
  10. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  11. 20244D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenescited by 185
  12. 2025Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Controlcited by 184
  13. 2021InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Renderingcited by 180
  14. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 176
  15. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 161
  16. 2023SparseGS: Sparse View Synthesis using 3D Gaussian Splattingcited by 134
  17. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  18. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  19. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  20. 2023F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectoriescited by 118
  21. 2021Pathdreamer: A World Model for Indoor Navigationcited by 117
  22. 2023Consistent View Synthesis with Pose-Guided Diffusion Modelscited by 117
  23. 2021HDR-NeRF: High Dynamic Range Neural Radiance Fieldscited by 113
  24. 2021NeRF-VAE: A Geometry Aware 3D Scene Generative Modelcited by 111
  25. 2022Vision Transformer for NeRF-Based View Synthesis from a Single Input Imagecited by 104
  26. 2023Learning to Render Novel Views from Wide-Baseline Stereo Pairscited by 103
  27. 2021NeuTex: Neural Texture Mapping for Volumetric Neural Renderingcited by 98
  28. 2021NeRF-SR: High-Quality Neural Radiance Fields using Supersamplingcited by 95
  29. 2022EventNeRF: Neural Radiance Fields from a Single Colour Event Cameracited by 92
  30. 2024SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpointscited by 92
  31. 2024V3D: Video Diffusion Models are Effective 3D Generatorscited by 88
  32. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  33. 2022Differentiable Point-Based Radiance Fields for Efficient View Synthesiscited by 86
  34. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  35. 2021Learning Indoor Inverse Rendering with 3D Spatially-Varying Lightingcited by 82
  36. 2022InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Imagescited by 82
  37. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 81
  38. 2023GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformerscited by 75

50 most cited of 206 All 206 (JSON)