KAO: Kernel-Adaptive Optimization in Diffusion for Satellite Image

• URL: http://arxiv.org/abs/2511.02462v1
• Date: Tue, 04 Nov 2025 10:44:36 GMT
• Title: KAO: Kernel-Adaptive Optimization in Diffusion for Satellite Image
• Abstract summary: KAO is a novel framework that utilizes Kernel-Adaptive Optimization within diffusion models for satellite image inpainting.<n> KAO is specifically designed to address the challenges posed by very high-resolution (VHR) satellite datasets.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Rethinking Satellite Image Restoration for Onboard AI: A Lightweight Learning-Based Approach [0.0]
  Satellite image restoration aims to improve image quality by compensating for degradations introduced by the imaging system and acquisition conditions.<n>Traditional restoration pipelines are computationally intensive and slow, making them unsuitable for onboard environments.<n>We introduce ConvBEERS: a light and non-generative residual convolutional network trained on simulated satellite data.
  arXiv  Detail & Related papers  (2026-04-14T14:37:26Z)
• Energy-oriented Diffusion Bridge for Image Restoration with Foundational Diffusion Models [65.20192162889253]
  We propose an Energy-oriented diffusion Bridge (E-Bridge) framework to approximate a set of low-cost manifold geodesic trajectories.<n>We achieve this by designing a novel bridge process that evolves over a shorter time horizon and makes the reverse process start from an entropy-regularized point.<n>We show that our E-Bridge achieves state-of-the-art performance across various image restoration tasks while enabling high-quality recovery with a single or fewer sampling steps.
  arXiv  Detail & Related papers  (2026-04-13T04:42:55Z)
• Finetuning-Free Personalization of Text to Image Generation via Hypernetworks [15.129799519953139]
  We introduce fine-tuning-free personalization via Hypernetworks that predict LoRA-adapted weights directly from subject images.<n>Our approach achieves strong personalization performance and highlights the promise of hypernetworks as a scalable and effective direction for open-category personalization.
  arXiv  Detail & Related papers  (2025-11-05T03:31:33Z)
• ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration [75.0053551643052]
  We introduce ZipIR, a novel framework that enhances efficiency, scalability, and long-range modeling for high-res image restoration.<n>ZipIR employs a highly compressed latent representation that compresses image 32x, effectively reducing the number of spatial tokens.<n>ZipIR surpasses existing diffusion-based methods, offering unmatched speed and quality in restoring high-resolution images from severely degraded inputs.
  arXiv  Detail & Related papers  (2025-04-11T14:49:52Z)
• Gaussian Splatting for Efficient Satellite Image Photogrammetry [9.965306860657472]
  We show how the standard Gaussian splatting framework can be adapted for remote sensing.<n>This enables us to achieve state-of-the-art performance in just a few minutes.
  arXiv  Detail & Related papers  (2024-12-17T16:11:14Z)
• Efficient Denoising Method to Improve The Resolution of Satellite Images [0.0]
  High-resolution satellite images help to identify smaller features on the ground and classification of ground cover types. Small satellites have weaker spatial resolution, and preprocessing using recent generative models made it possible to enhance the resolution of these satellite images.
  arXiv  Detail & Related papers  (2024-11-11T03:33:53Z)
• Learning Efficient and Effective Trajectories for Differential Equation-based Image Restoration [59.744840744491945]
  In this paper, we reformulate the trajectory optimization of this kind of method, focusing on enhancing both reconstruction quality and efficiency.<n>To mitigate the considerable computational burden associated with iterative sampling, we propose cost-aware trajectory distillation.<n>We fine-tune a foundational diffusion model (FLUX) with 12B parameters by using our algorithms, producing a unified framework for handling 7 kinds of image restoration tasks.
  arXiv  Detail & Related papers  (2024-10-07T07:46:08Z)
• Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors [75.24313405671433]
  Diffusion-based image super-resolution (SR) methods have achieved remarkable success by leveraging large pre-trained text-to-image diffusion models as priors. We introduce a novel one-step SR model, which significantly addresses the efficiency issue of diffusion-based SR methods. Unlike existing fine-tuning strategies, we designed a degradation-guided Low-Rank Adaptation (LoRA) module specifically for SR.
  arXiv  Detail & Related papers  (2024-09-25T16:15:21Z)
• Timestep-Aware Diffusion Model for Extreme Image Rescaling [47.89362819768323]
  We propose a novel framework called Timestep-Aware Diffusion Model (TADM) for extreme image rescaling.<n>TADM performs rescaling operations in the latent space of a pre-trained autoencoder.<n>It effectively leverages powerful natural image priors learned by a pre-trained text-to-image diffusion model.
  arXiv  Detail & Related papers  (2024-08-17T09:51:42Z)
• Coherent and Multi-modality Image Inpainting via Latent Space Optimization [61.99406669027195]
  PILOT (intextbfPainting vtextbfIa textbfLatent textbfOptextbfTimization) is an optimization approach grounded on a novel textitsemantic centralization and textitbackground preservation loss. Our method searches latent spaces capable of generating inpainted regions that exhibit high fidelity to user-provided prompts while maintaining coherence with the background.
  arXiv  Detail & Related papers  (2024-07-10T19:58:04Z)
• SatDiffMoE: A Mixture of Estimation Method for Satellite Image Super-resolution with Latent Diffusion Models [3.839322642354617]
  We propose a novel diffusion-based fusion algorithm called textbfSatDiffMoE. Our algorithm is highly flexible and allows training and inference on arbitrary number of low-resolution images. Experimental results show that our proposed SatDiffMoE method achieves superior performance for the satellite image super-resolution tasks.
  arXiv  Detail & Related papers  (2024-06-14T17:58:28Z)
• Diffusion Enhancement for Cloud Removal in Ultra-Resolution Remote Sensing Imagery [48.14610248492785]
  Cloud layers severely compromise the quality and effectiveness of optical remote sensing (RS) images. Existing deep-learning (DL)-based Cloud Removal (CR) techniques encounter difficulties in accurately reconstructing the original visual authenticity and detailed semantic content of the images. This work proposes enhancements at the data and methodology fronts to tackle this challenge.
  arXiv  Detail & Related papers  (2024-01-25T13:14:17Z)
• JoReS-Diff: Joint Retinex and Semantic Priors in Diffusion Model for Low-light Image Enhancement [69.6035373784027]
  Low-light image enhancement (LLIE) has achieved promising performance by employing conditional diffusion models. Previous methods may neglect the importance of a sufficient formulation of task-specific condition strategy. We propose JoReS-Diff, a novel approach that incorporates Retinex- and semantic-based priors as the additional pre-processing condition.
  arXiv  Detail & Related papers  (2023-12-20T08:05:57Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.