mlsanityData to 7 Oct 2026

Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image

arXiv 2012.09855 ↗First posted 17 Dec 2020cs.CV cs.GRcited by 239

Not on the map. Why?

Cited by 43 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce the problem of perpetual view generation - long-range generation of novel views corresponding to an arbitrarily long camera trajectory given a single image. This is a challenging problem that goes far beyond the capabilities of current view synthesis methods, which quickly degenerate when presented with large camera motions. Methods for video generation also have limited ability to produce long sequences and are often agnostic to scene geometry. We take a hybrid approach that integrates both geometry and image synthesis in an iterative `render, refine and repeat' framework, allowing for long-range generation that cover large distances after hundreds of frames. Our approach can be trained from a set of monocular video sequences. We propose a dataset of aerial footage of coastal scenes, and compare our method with recent view synthesis and conditional video generation baselines, showing that it can generate plausible scenes for much longer time horizons over large camera trajectories compared to existing methods. Project page at https://infinite-nature.github.io/.

Key facts. Cited by 239 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 21; 2023: 39; 2024: 50; 2025: 83; 2026: 39.

239 papers.

Sort:

By area:

  1. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  2. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
  3. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 569
  4. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  5. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
  6. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 448
  7. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  8. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  9. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
  10. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  11. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 241
  12. 2024A Survey on 3D Gaussian Splattingcited by 221
38 more
  1. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 197
  2. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 179
  3. 2023SceneScape: Text-Driven Consistent Scene Generationcited by 160
  4. 2023WonderJourney: Going from Anywhere to Everywherecited by 157
  5. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 139
  6. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  7. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  8. 2021Pathdreamer: A World Model for Indoor Navigationcited by 117
  9. 2023Consistent View Synthesis with Pose-Guided Diffusion Modelscited by 117
  10. 2024Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Controlcited by 117
  11. 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimationcited by 116
  12. 2022Generating Long Videos of Dynamic Scenescited by 113
  13. 2023ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Imagecited by 109
  14. 2023Learning to Render Novel Views from Wide-Baseline Stereo Pairscited by 103
  15. 20243D Gaussian as a New Era: A Surveycited by 102
  16. 2025VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memorycited by 102
  17. 2021Geometry-Free View Synthesis: Transformers and no 3D Priorscited by 99
  18. 2024Wonderland: Navigating 3D Scenes from a Single Imagecited by 98
  19. 2025CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Modelscited by 97
  20. 2023Generative Image Dynamicscited by 93
  21. 2023Monocular Depth Estimation using Diffusion Modelscited by 87
  22. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  23. 2022InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Imagescited by 82
  24. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 81
  25. 2021Learning to Stylize Novel Viewscited by 76
  26. 2023Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFscited by 76
  27. 2023Long-Term Photometric Consistent Novel View Synthesis with Diffusion Modelscited by 76
  28. 2023CityDreamer: Compositional Generative Model of Unbounded 3D Citiescited by 75
  29. 2023GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformerscited by 75
  30. 2025Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generationcited by 75
  31. 2023SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collectionscited by 72
  32. 2024GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warpingcited by 72
  33. 2022NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesiscited by 71
  34. 2024TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformerscited by 71
  35. 2025MotionStream: Real-Time Video Generation with Interactive Motion Controlscited by 71
  36. 2021Aligning Latent and Image Spaces to Connect the Unconnectablecited by 70
  37. 20233D-aware Image Generation using 2D Diffusion Modelscited by 69
  38. 2023InfiniCity: Infinite-Scale City Synthesiscited by 68

50 most cited of 239 All 239 (JSON)