用流模型加速遥感图像超分，支持任意尺度重建。
Flow-based Gaussian Splatting for Continuous-Scale Remote Sensing Image Super-Resolution
- 基于流匹配建模高低分辨率细节关系，减少生成步骤。
- 推理速度显著提升，40~1000步的扩散模型变为高效单步生成。
- 结合2D高斯点阵实现任意位置灵活重建，适合遥感应用。
高分辨率遥感图像对地球观测至关重要，但受传感器限制和成本制约难以获取。近年来，生成式超分辨率方法（尤其是扩散模型）取得进展，但通常需要40至1000步的迭代推理，且在连续尺度超分场景下灵活性不足。为此，我们提出FlowGS，一种用于遥感图像任意尺度超分的生成重建框架。FlowGS建模高低分辨率图像间的高频细节表征，通过流匹配（FM）学习从噪声到细节先验的连续概率流，并施加捷径一致性约束，从而降低生成复杂度并提升推理效率。此外，采用2D高斯点阵构建连续特征场，实现任意查询位置的灵活重建。实验表明，FlowGS在连续与固定尺度超分设置中均达到与现有方法相当的感知质量，且推理效率大幅提升。
原文摘要 · Abstract (English)
High-resolution remote sensing images (RSIs) are crucial for Earth observation applications, yet acquiring them is often limited by sensor constraints and costs. In recent years, generative super-resolution (SR) methods, particularly diffusion models, have made significant progress. However, they typically require slow iterative inference with 40--1000 steps and exhibit limited flexibility in continuous-scale SR settings. To address these issues, we propose FlowGS, a generative reconstruction framework for arbitrary-scale SR of RSIs. FlowGS models the high-frequency detail representations between high- and low-resolution images and learns a continuous probability flow from noise to detail priors via flow matching (FM) constrained by shortcut consistency, thereby reducing generative complexity and improving inference efficiency. Additionally, we employ 2D Gaussian splatting to construct a continuous feature field, thereby enabling flexible reconstruction at arbitrary query locations. Experimental results show that FlowGS delivers competitive perceptual quality compared with existing methods in both continuous-scale and fixed-scale SR settings, with substantially improved inference efficiency.
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。