arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.02462cs.CV
收藏

KAO:用于卫星图像的扩散模型中的核自适应优化

KAO: Kernel-Adaptive Optimization in Diffusion for Satellite Image

Chulalongkorn University(朱拉隆功大学)

Teerapong Panboonyuen

AI总结:

本文提出KAO框架,通过在扩散模型中引入核自适应优化、潜在空间条件化和显式传播,高效准确地实现了超高分辨率卫星图像修复,平衡了预条件模型的效率与后条件模型的灵活性。

摘要:

卫星图像修复是遥感中的一项关键任务,准确恢复缺失或遮挡区域对于稳健的图像分析至关重要。在本文中,我们提出了KAO,这是一种在扩散模型中利用核自适应优化进行卫星图像修复的新颖框架。KAO专为解决超高分辨率(VHR)卫星数据集(如DeepGlobe和Massachusetts Roads Dataset)带来的挑战而设计。与依赖需要大量重训练的预条件模型或具有显著计算开销的后条件模型的现有方法不同,KAO引入了潜在空间条件化方法,优化紧凑的潜在空间以实现高效且准确的修复。此外,我们将显式传播融入扩散过程,促进前后向融合,从而提高了该方法的稳定性和精度。实验结果表明,KAO为VHR卫星图像恢复设定了新的基准,提供了一种可扩展、高性能的解决方案,平衡了预条件模型的效率与后条件模型的灵活性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑