# Genesis: A Generative Engine for Hierarchical Satellite Image Synthesis

arXiv: https://arxiv.org/abs/2609.02683 · HTML: https://mlsanity.com/paper/2609.02683/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 51 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Builds on (most cited first, 26 of 26)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting](https://mlsanity.com/paper/2307.12348/) (2023)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions](https://mlsanity.com/paper/2003.01826/) (2020)
- [PixelDiT: Pixel Diffusion Transformers for Image Generation](https://mlsanity.com/paper/2511.20645/) (2025)
- [Mixture of Diffusers for scene composition and high resolution image generation](https://mlsanity.com/paper/2302.02412/) (2023)
- [GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis](https://mlsanity.com/paper/2404.06637/) (2024)
- [Segment Anything Model for Road Network Graph Extraction](https://mlsanity.com/paper/2403.16051/) (2024)
- [There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-training](https://mlsanity.com/paper/2510.12586/) (2025)
- [ZoomLDM: Latent Diffusion Model for multi-scale image generation](https://mlsanity.com/paper/2411.16969/) (2024)
- [EarthSynth: Generating Informative Earth Observation with Diffusion Models](https://mlsanity.com/paper/2505.12108/) (2025)
- [VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics](https://mlsanity.com/paper/2511.07744/) (2025)
- [Procedural 3D Terrain Generation using Generative Adversarial Networks](https://mlsanity.com/paper/2010.06411/) (2020)
- [TerraDiT-Omega: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive](https://mlsanity.com/paper/2606.31029/) (2026)

## Abstract (arXiv)

Earth observation is fundamentally multi-scale; geospatial tasks span varied resolutions, and satellite imagery is organized into cascading tile pyramids that nest fine detail within wide coverage. Current generative models of satellite imagery, however, operate along a single axis: they either zoom to enhance a single tile's resolution or pan to extend imagery at a fixed scale. As a result, no existing method produces a complete pyramid that stays consistent across both scale and space, where a high-zoom tile must agree with the coarse context it refines and with the neighbors it meets. Motivated by this gap, we introduce a new task, multi-scale tile completion: given a sparse set of seed tiles at arbitrary zoom levels and positions, synthesize a complete, uniform quadtree that is globally consistent across both scale and space. We approach this task with Genesis, a generative engine that brings both axes together by composing two specialized operators over the quadtree: a vertical super-resolution model and a horizontal mask-based outpainting model, producing pyramids that are consistent across zoom levels and seamless across neighboring tiles. Each operator achieves state-of-the-art results on its subtask, and the engine propagates sparse seeds into seamless, multi-resolution maps from any initial configuration. To evaluate the task and benchmark Genesis, we introduce dense500, a fully observed multi-scale pyramid dataset spanning diverse geographic regions, together with a suite of pyramid-level metrics. Code, models, and our dataset are available at https://github.com/mvrl/genesis.