KAO通过自适应核优化，高效修复高分辨率卫星图像缺失区域。
KAO: Kernel-Adaptive Optimization in Diffusion for Satellite Image
- 在扩散模型潜空间中引入自适应核优化，实现高效图像修复。
- 在DeepGlobe和马萨诸塞道路数据集上表现优于现有方法，提升修复精度。
- 适合需要高效率与高精度的遥感图像修复任务，尤其适用于大尺寸卫星图。
卫星图像修复是遥感中的关键任务，准确恢复缺失或遮挡区域对稳健图像分析至关重要。本文提出KAO，一种在扩散模型中引入核自适应优化的新框架，用于卫星图像修复。KAO专为处理超高分辨率（VHR）卫星数据集（如DeepGlobe和Massachusetts Roads Dataset）设计。与依赖预训练重训或计算开销大的后处理模型不同，KAO采用潜空间条件化策略，优化紧凑潜空间以实现高效且精准的修复。此外，我们引入显式传播机制，促进前向-反向信息融合，提升方法的稳定性和精度。实验表明，KAO在VHR卫星图像重建上树立了新基准，提供了一个兼顾预处理模型效率与后处理模型灵活性的可扩展高性能解决方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。