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

arXiv: https://arxiv.org/abs/2012.09855 · HTML: https://mlsanity.com/paper/2012.09855/

## Key facts

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

## Built on by (most cited first, 30 of 239)

- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [CameraCtrl: Enabling Camera Control for Text-to-Video Generation](https://mlsanity.com/paper/2404.02101/) (2024)
- [Splatter Image: Ultra-Fast Single-View 3D Reconstruction](https://mlsanity.com/paper/2312.13150/) (2023)
- [DepthSplat: Connecting Gaussian Splatting and Depth](https://mlsanity.com/paper/2410.13862/) (2024)
- [Generative Novel View Synthesis with 3D-Aware Diffusion Models](https://mlsanity.com/paper/2304.02602/) (2023)
- [Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models](https://mlsanity.com/paper/2303.11989/) (2023)
- [No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images](https://mlsanity.com/paper/2410.24207/) (2024)
- [A Survey on 3D Gaussian Splatting](https://mlsanity.com/paper/2401.03890/) (2024)
- [WonderWorld: Interactive 3D Scene Generation from a Single Image](https://mlsanity.com/paper/2406.09394/) (2024)
- [NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion](https://mlsanity.com/paper/2302.10109/) (2023)
- [SceneScape: Text-Driven Consistent Scene Generation](https://mlsanity.com/paper/2302.01133/) (2023)
- [WonderJourney: Going from Anywhere to Everywhere](https://mlsanity.com/paper/2312.03884/) (2023)
- [ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model](https://mlsanity.com/paper/2408.16767/) (2024)
- [Unconstrained Scene Generation with Locally Conditioned Radiance Fields](https://mlsanity.com/paper/2104.00670/) (2021)
- [State of the Art on Diffusion Models for Visual Computing](https://mlsanity.com/paper/2310.07204/) (2023)
- [Pathdreamer: A World Model for Indoor Navigation](https://mlsanity.com/paper/2105.08756/) (2021)
- [Consistent View Synthesis with Pose-Guided Diffusion Models](https://mlsanity.com/paper/2303.17598/) (2023)
- [Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control](https://mlsanity.com/paper/2405.17414/) (2024)
- [The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation](https://mlsanity.com/paper/2306.01923/) (2023)
- [Generating Long Videos of Dynamic Scenes](https://mlsanity.com/paper/2206.03429/) (2022)
- [ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image](https://mlsanity.com/paper/2310.17994/) (2023)
- [Learning to Render Novel Views from Wide-Baseline Stereo Pairs](https://mlsanity.com/paper/2304.08463/) (2023)
- [3D Gaussian as a New Era: A Survey](https://mlsanity.com/paper/2402.07181/) (2024)
- [VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory](https://mlsanity.com/paper/2506.18903/) (2025)
- [Geometry-Free View Synthesis: Transformers and no 3D Priors](https://mlsanity.com/paper/2104.07652/) (2021)
- [Wonderland: Navigating 3D Scenes from a Single Image](https://mlsanity.com/paper/2412.12091/) (2024)

## 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/.