# Persistent Nature: A Generative Model of Unbounded 3D Worlds

arXiv: https://arxiv.org/abs/2303.13515 · HTML: https://mlsanity.com/paper/2303.13515/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Placed in Video-generation world models and simulators, one of 11 directions in World models.
- Builds on 85 of its 105 references that are in the map.
- First posted on arXiv 23 Mar 2023.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)

## Builds on (most cited first, 30 of 85)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines](https://mlsanity.com/paper/1905.00889/) (2019)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [MoCoGAN: Decomposing Motion and Content for Video Generation](https://mlsanity.com/paper/1707.04993/) (2017)
- [StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis](https://mlsanity.com/paper/2110.08985/) (2021)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [Generating Videos with Scene Dynamics](https://mlsanity.com/paper/1609.02612/) (2016)
- [SynSin: End-to-end View Synthesis from a Single Image](https://mlsanity.com/paper/1912.08804/) (2019)
- [StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2](https://mlsanity.com/paper/2112.14683/) (2021)

## Built on by (most cited first, 30 of 44)

- [WonderWorld: Interactive 3D Scene Generation from a Single Image](https://mlsanity.com/paper/2406.09394/) (2024)
- [WonderJourney: Going from Anywhere to Everywhere](https://mlsanity.com/paper/2312.03884/) (2023)
- [CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models](https://mlsanity.com/paper/2503.10592/) (2025)
- [CityDreamer: Compositional Generative Model of Unbounded 3D Cities](https://mlsanity.com/paper/2309.00610/) (2023)
- [WoW: Towards a World omniscient World model Through Embodied Interaction](https://mlsanity.com/paper/2509.22642/) (2025)
- [NeRFiller: Completing Scenes via Generative 3D Inpainting](https://mlsanity.com/paper/2312.04560/) (2023)
- [Generative Gaussian Splatting for Unbounded 3D City Generation](https://mlsanity.com/paper/2406.06526/) (2024)
- [Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion](https://mlsanity.com/paper/2407.13759/) (2024)
- [SynCity: Training-Free Generation of 3D Worlds](https://mlsanity.com/paper/2503.16420/) (2025)
- [Learning 3D Persistent Embodied World Models](https://mlsanity.com/paper/2505.05495/) (2025)
- [UrbanWorld: An Urban World Model for 3D City Generation](https://mlsanity.com/paper/2407.11965/) (2024)
- [3D Scene Generation: A Survey](https://mlsanity.com/paper/2505.05474/) (2025)
- [CityGen: Infinite and Controllable City Layout Generation](https://mlsanity.com/paper/2312.01508/) (2023)
- [CityX: Controllable Procedural Content Generation for Unbounded 3D Cities](https://mlsanity.com/paper/2407.17572/) (2024)
- [iNVS: Repurposing Diffusion Inpainters for Novel View Synthesis](https://mlsanity.com/paper/2310.16167/) (2023)
- [Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Image](https://mlsanity.com/paper/2308.10257/) (2023)
- [NuiScene: Exploring Efficient Generation of Unbounded Outdoor Scenes](https://mlsanity.com/paper/2503.16375/) (2025)
- [Compositional Generative Model of Unbounded 4D Cities](https://mlsanity.com/paper/2501.08983/) (2025)
- [Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion](https://mlsanity.com/paper/2507.04403/) (2025)
- [Urban Scene Diffusion through Semantic Occupancy Map](https://mlsanity.com/paper/2403.11697/) (2024)
- [COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generation](https://mlsanity.com/paper/2407.11294/) (2024)
- [Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2503.14537/) (2025)
- [Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion](https://mlsanity.com/paper/2511.18734/) (2025)
- [TRELLISWorld: Training-Free World Generation from Object Generators](https://mlsanity.com/paper/2510.23880/) (2025)
- [WorldClaw: Agentic 3D Open-World Generation at Scale](https://mlsanity.com/paper/2608.05248/) (2026)
- [ScenePainter: Semantically Consistent Perpetual 3D Scene Generation with Concept Relation Alignment](https://mlsanity.com/paper/2507.19058/) (2025)
- [Proc-GS: Procedural Building Generation for City Assembly with 3D Gaussians](https://mlsanity.com/paper/2412.07660/) (2024)
- [MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts](https://mlsanity.com/paper/2511.20415/) (2025)
- [Locally Adaptive Neural 3D Morphable Models](https://mlsanity.com/paper/2401.02937/) (2024)
- [6Img-to-3D: Few-Image Large-Scale Outdoor Driving Scene Reconstruction](https://mlsanity.com/paper/2404.12378/) (2024)

## Abstract (arXiv)

Despite increasingly realistic image quality, recent 3D image generative models often operate on 3D volumes of fixed extent with limited camera motions. We investigate the task of unconditionally synthesizing unbounded nature scenes, enabling arbitrarily large camera motion while maintaining a persistent 3D world model. Our scene representation consists of an extendable, planar scene layout grid, which can be rendered from arbitrary camera poses via a 3D decoder and volume rendering, and a panoramic skydome. Based on this representation, we learn a generative world model solely from single-view internet photos. Our method enables simulating long flights through 3D landscapes, while maintaining global scene consistency--for instance, returning to the starting point yields the same view of the scene. Our approach enables scene extrapolation beyond the fixed bounds of current 3D generative models, while also supporting a persistent, camera-independent world representation that stands in contrast to auto-regressive 3D prediction models. Our project page: https://chail.github.io/persistent-nature/.