Flow-based Gaussian Splatting for Continuous-Scale Remote Sensing Image Super-Resolution

2026-05-21

AI Summary

This work addresses the challenges of high-resolution remote sensing image reconstruction, which is constrained by sensor costs and acquisition conditions, as well as the inefficiency and limited scalability of existing generative super-resolution methods. To overcome these limitations, the authors propose FlowGS, a novel framework that introduces 2D Gaussian Splatting into remote sensing image super-resolution for the first time. By constructing a continuous feature field, FlowGS enables efficient arbitrary-scale reconstruction. Additionally, a flow matching mechanism with shortcut consistency is designed to model the distribution of high-frequency details between low- and high-resolution images, thereby reducing generation complexity. The method achieves superior perceptual quality on both fixed- and continuous-scale super-resolution tasks while significantly improving inference efficiency.

Abstract

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.

Problem

• remote sensing image super-resolution
• continuous-scale super-resolution
• generative super-resolution
• inference efficiency
• high-resolution imagery

Innovation

• Flow Matching
• Gaussian Splatting
• Continuous-Scale Super-Resolution
• Generative Reconstruction
• Remote Sensing Image