mlsanityData to 7 Oct 2026

InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images

arXiv 2207.11148 ↗First posted 22 Jul 2022cs.CVcited by 82

Not on the map. Why?

Cited by 24 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a method for learning to generate unbounded flythrough videos of natural scenes starting from a single view, where this capability is learned from a collection of single photographs, without requiring camera poses or even multiple views of each scene. To achieve this, we propose a novel self-supervised view generation training paradigm, where we sample and rendering virtual camera trajectories, including cyclic ones, allowing our model to learn stable view generation from a collection of single views. At test time, despite never seeing a video during training, our approach can take a single image and generate long camera trajectories comprised of hundreds of new views with realistic and diverse content. We compare our approach with recent state-of-the-art supervised view generation methods that require posed multi-view videos and demonstrate superior performance and synthesis quality.

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). Builds on 73 of its 94 references that are in the map. First posted on arXiv 22 Jul 2022.

Builds on

73 of 94 references.

References · 73

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  8. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  9. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  10. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  11. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  12. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
38 more
  1. 2018Demystifying MMD GANscited by 1,268
  2. 2020Neural Sparse Voxel Fieldscited by 959
  3. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  4. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  5. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  6. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  7. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  8. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  9. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 523
  10. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  11. 2016Generating Videos with Scene Dynamicscited by 376
  12. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  13. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  14. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 285
  15. 2020Softmax Splatting for Video Frame Interpolationcited by 276
  16. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  17. 2016Unsupervised Learning for Physical Interaction through Video Predictioncited by 256
  18. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  19. 2018Stochastic Video Generation with a Learned Priorcited by 244
  20. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 239
  21. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 236
  22. 2020Free View Synthesiscited by 231
  23. 2021Large Scale Image Completion via Co-Modulated Generative Adversarial Networkscited by 219
  24. 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
  25. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 206
  26. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  27. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  28. 2021CodeNeRF: Disentangled Neural Radiance Fields for Object Categoriescited by 183
  29. 2017Decomposing Motion and Content for Natural Video Sequence Predictioncited by 168
  30. 2021A Good Image Generator Is What You Need for High-Resolution Video Synthesiscited by 162
  31. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  32. 20193D Ken Burns Effect from a Single Imagecited by 128
  33. 2018Learning to Decompose and Disentangle Representations for Video Predictioncited by 120
  34. 2021Pathdreamer: A World Model for Indoor Navigationcited by 117
  35. 2021Geometry-Free View Synthesis: Transformers and no 3D Priorscited by 99
  36. 2021GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worldscited by 98
  37. 2018Extreme View Synthesiscited by 94
  38. 2019High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networkscited by 88

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 24; 2024: 20; 2025: 28; 2026: 5.

82 papers.

Sort:

By area:

  1. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 569
  2. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
  3. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  4. 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
  5. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 197
  6. 2023SceneScape: Text-Driven Consistent Scene Generationcited by 160
  7. 2023WonderJourney: Going from Anywhere to Everywherecited by 157
  8. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  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. 2025CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Modelscited by 97
  12. 2023Generative Image Dynamicscited by 93
38 more
  1. 2023Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFscited by 76
  2. 2023CityDreamer: Compositional Generative Model of Unbounded 3D Citiescited by 75
  3. 2023SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collectionscited by 72
  4. 2024GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warpingcited by 72
  5. 2025MotionStream: Real-Time Video Generation with Interactive Motion Controlscited by 71
  6. 20233D-aware Image Generation using 2D Diffusion Modelscited by 69
  7. 2023InfiniCity: Infinite-Scale City Synthesiscited by 68
  8. 2024MultiDiff: Consistent Novel View Synthesis from a Single Imagecited by 67
  9. 2023NeRFiller: Completing Scenes via Generative 3D Inpaintingcited by 62
  10. 2024Advances in 3D Generation: A Surveycited by 62
  11. 2024LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generationcited by 53
  12. 2022DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Modelscited by 51
  13. 2022RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Modelscited by 45
  14. 2023Persistent Nature: A Generative Model of Unbounded 3D Worldscited by 44
  15. 2023Pyramid Diffusion for Fine 3D Large Scene Generationcited by 44
  16. 2024Generative Gaussian Splatting for Unbounded 3D City Generationcited by 43
  17. 2025GenFusion: Closing the Loop between Reconstruction and Generation via Videoscited by 41
  18. 2024Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusioncited by 39
  19. 2025SynCity: Training-Free Generation of 3D Worldscited by 30
  20. 20243D-SceneDreamer: Text-Driven 3D-Consistent Scene Generationcited by 29
  21. 2023UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fieldscited by 26
  22. 2025StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generationcited by 26
  23. 2024MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinementcited by 24
  24. 20253D Scene Generation: A Surveycited by 24
  25. 2024Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpaintingcited by 23
  26. 2023CityGen: Infinite and Controllable City Layout Generationcited by 22
  27. 2025WorldCraft: Photo-Realistic 3D World Creation and Customization via LLM Agentscited by 21
  28. 2023iNVS: Repurposing Diffusion Inpainters for Novel View Synthesiscited by 20
  29. 2023Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Imagecited by 19
  30. 2024Pano2Room: Novel View Synthesis from a Single Indoor Panoramacited by 16
  31. 2025Compositional Generative Model of Unbounded 4D Citiescited by 16
  32. 2023Generative Powers of Tencited by 15
  33. 2026Streaming Autoregressive Video Generation via Diagonal Distillationcited by 15
  34. 2024Urban Scene Diffusion through Semantic Occupancy Mapcited by 14
  35. 2025Agentic 3D Scene Generation with Spatially Contextualized VLMscited by 14
  36. 2022Towards Smooth Video Compositioncited by 12
  37. 2022Bridging Implicit and Explicit Geometric Transformation for Single-Image View Synthesiscited by 11
  38. 2023SinMPI: Novel View Synthesis from a Single Image with Expanded Multiplane Imagescited by 11

50 most cited of 82 All 82 (JSON)