mlsanityData to 7 Oct 2026

Neural Rerendering in the Wild

arXiv 1904.04290 ↗First posted 8 Apr 2019cs.CV cs.GRcited by 121

Not on the map. Why?

Abstract (arXiv)

We explore total scene capture -- recording, modeling, and rerendering a scene under varying appearance such as season and time of day. Starting from internet photos of a tourist landmark, we apply traditional 3D reconstruction to register the photos and approximate the scene as a point cloud. For each photo, we render the scene points into a deep framebuffer, and train a neural network to learn the mapping of these initial renderings to the actual photos. This rerendering network also takes as input a latent appearance vector and a semantic mask indicating the location of transient objects like pedestrians. The model is evaluated on several datasets of publicly available images spanning a broad range of illumination conditions. We create short videos demonstrating realistic manipulation of the image viewpoint, appearance, and semantic labeling. We also compare results with prior work on scene reconstruction from internet photos.

Key facts. Cited by 121 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 47; 2022: 22; 2023: 30; 2024: 15; 2025: 4; 2026: 3.

121 papers.

Sort:

By area:

  1. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
  2. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  3. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  4. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  5. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  6. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  7. 2021Advances in Neural Renderingcited by 365
  8. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 365
  9. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 332
  10. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  11. 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
  12. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 222
38 more
  1. 2021HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fieldscited by 210
  2. 2024VastGaussian: Vast 3D Gaussians for Large Scene Reconstructioncited by 209
  3. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
  4. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  5. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  6. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 182
  7. 2023GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesiscited by 170
  8. 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
  9. 2021Editable Free-viewpoint Video Using a Layered Neural Representationcited by 148
  10. 2022StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learningcited by 140
  11. 2021Hallucinated Neural Radiance Fields in the Wildcited by 130
  12. 2023Consistent View Synthesis with Pose-Guided Diffusion Modelscited by 117
  13. 2024Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collectionscited by 117
  14. 2021NeRF for Outdoor Scene Relightingcited by 114
  15. 2021Geometry-Free View Synthesis: Transformers and no 3D Priorscited by 99
  16. 2023Grid-guided Neural Radiance Fields for Large Urban Scenescited by 99
  17. 2021T"oRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesiscited by 88
  18. 2022Differentiable Point-Based Radiance Fields for Efficient View Synthesiscited by 86
  19. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  20. 2021Learning Indoor Inverse Rendering with 3D Spatially-Varying Lightingcited by 82
  21. 2023Neural Point Catacaustics for Novel-View Synthesis of Reflectionscited by 81
  22. 2022Neural 3D Reconstruction in the Wildcited by 79
  23. 2021Learning to Stylize Novel Viewscited by 76
  24. 2024Fully Explicit Dynamic Gaussian Splattingcited by 75
  25. 2024MultiDiff: Consistent Novel View Synthesis from a Single Imagecited by 67
  26. 2021Shelf-Supervised Mesh Prediction in the Wildcited by 65
  27. 2021Direct-PoseNet: Absolute Pose Regression with Photometric Consistencycited by 61
  28. 2022Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulationcited by 57
  29. 2023Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedracited by 57
  30. 2024Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collectionscited by 56
  31. 2023Urban Radiance Field Representation with Deformable Neural Mesh Primitivescited by 55
  32. 2023CamP: Camera Preconditioning for Neural Radiance Fieldscited by 55
  33. 2021Style and Pose Control for Image Synthesis of Humans from a Single Monocular Viewcited by 53
  34. 2021Multimodal Image Synthesis and Editing: The Generative AI Eracited by 52
  35. 2022DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Modelscited by 51
  36. 2021Free-viewpoint Indoor Neural Relighting from Multi-view Stereocited by 50
  37. 2022READ: Large-Scale Neural Scene Rendering for Autonomous Drivingcited by 50
  38. 2021Self-supervised Outdoor Scene Relightingcited by 48

50 most cited of 121 All 121 (JSON)