# KAO: Kernel-Adaptive Optimization in Diffusion for Satellite Image

arXiv: https://arxiv.org/abs/2511.02462 · HTML: https://mlsanity.com/paper/2511.02462/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 4 Nov 2025.

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

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model](https://mlsanity.com/paper/2212.05034/) (2022)
- [DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images](https://mlsanity.com/paper/1805.06561/) (2018)
- [Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting](https://mlsanity.com/paper/2212.06909/) (2022)
- [Inpaint Anything: Segment Anything Meets Image Inpainting](https://mlsanity.com/paper/2304.06790/) (2023)
- [ProPainter: Improving Propagation and Transformer for Video Inpainting](https://mlsanity.com/paper/2309.03897/) (2023)
- [RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation](https://mlsanity.com/paper/2211.09869/) (2022)
- [Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models](https://mlsanity.com/paper/2307.00619/) (2023)
- [DiffusionSat: A Generative Foundation Model for Satellite Imagery](https://mlsanity.com/paper/2312.03606/) (2023)
- [TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation](https://mlsanity.com/paper/2204.05525/) (2022)
- [AVID: Any-Length Video Inpainting with Diffusion Model](https://mlsanity.com/paper/2312.03816/) (2023)
- [Inst-Inpaint: Instructing to Remove Objects with Diffusion Models](https://mlsanity.com/paper/2304.03246/) (2023)
- [NeRFiller: Completing Scenes via Generative 3D Inpainting](https://mlsanity.com/paper/2312.04560/) (2023)
- [Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image Inpainting](https://mlsanity.com/paper/2403.19898/) (2024)
- [DreamInpainter: Text-Guided Subject-Driven Image Inpainting with Diffusion Models](https://mlsanity.com/paper/2312.03771/) (2023)
- [Diverse Inpainting and Editing with GAN Inversion](https://mlsanity.com/paper/2307.15033/) (2023)
- [Taming Latent Diffusion Model for Neural Radiance Field Inpainting](https://mlsanity.com/paper/2404.09995/) (2024)
- [Personalized Face Inpainting with Diffusion Models by Parallel Visual Attention](https://mlsanity.com/paper/2312.03556/) (2023)
- [Denoising Diffusion Models for Inpainting of Healthy Brain Tissue](https://mlsanity.com/paper/2402.17307/) (2024)
- [Exploring the Capability of Text-to-Image Diffusion Models with Structural Edge Guidance for Multi-Spectral Satellite Image Inpainting](https://mlsanity.com/paper/2311.03008/) (2023)
- [Text Image Inpainting via Global Structure-Guided Diffusion Models](https://mlsanity.com/paper/2401.14832/) (2024)
- [SLCGC: A lightweight Self-supervised Low-pass Contrastive Graph Clustering Network for Hyperspectral Images](https://mlsanity.com/paper/2502.03497/) (2025)
- [SA-MixNet: Structure-aware Mixup and Invariance Learning for Scribble-supervised Road Extraction in Remote Sensing Images](https://mlsanity.com/paper/2403.01381/) (2024)

## Abstract (arXiv)

Satellite image inpainting is a crucial task in remote sensing, where accurately restoring missing or occluded regions is essential for robust image analysis. In this paper, we propose KAO, a novel framework that utilizes Kernel-Adaptive Optimization within diffusion models for satellite image inpainting. KAO is specifically designed to address the challenges posed by very high-resolution (VHR) satellite datasets, such as DeepGlobe and the Massachusetts Roads Dataset. Unlike existing methods that rely on preconditioned models requiring extensive retraining or postconditioned models with significant computational overhead, KAO introduces a Latent Space Conditioning approach, optimizing a compact latent space to achieve efficient and accurate inpainting. Furthermore, we incorporate Explicit Propagation into the diffusion process, facilitating forward-backward fusion, which improves the stability and precision of the method. Experimental results demonstrate that KAO sets a new benchmark for VHR satellite image restoration, providing a scalable, high-performance solution that balances the efficiency of preconditioned models with the flexibility of postconditioned models.