通过频域门控机制提升跨传感器遥感图像超分辨率质量
Spatial-Frequency Gated Swin Transformer for Cross-Sensor Remote Sensing Super-Resolution
- 在Swin Transformer中引入空间-频率门控前馈网络，分离低频结构与高频细节
- 在SEN2VENμS等3个真实数据集上均实现稳定提升，最高提升1.27dB PSNR
- 轻量级设计适合部署，适合遥感图像超分辨任务的结构保持需求
遥感单图超分辨率旨在从低分辨率观测中重建高分辨率图像，同时保留道路、建筑边界、田块边缘和地表覆盖变化等精细结构。基于Swin Transformer的模型（如Swin2SR）通过移位窗口自注意力提供强空间上下文建模，但其前馈网络仍为通用通道混合模块，未显式区分低频结构与残差细节。本文提出SFG-SwinSR，将标准Swin2SR的前馈网络替换为轻量级空间-频率门控前馈网络。该模块通过深度可分离低通分支估计平滑特征分量，减法获取残差细节，经空间精炼后通过瓶颈门控自适应重注入有用信息。在真实跨传感器数据集SEN2VENμS、OLI2MSI和SEN2NAIP，以及辅助合成的SpaceNet Challenge 3设置下实验表明，多数评估场景均有持续提升，性能优于近期Swin基线。结果表明，变压器前馈网络中的空间-频率变换为结构感知的跨传感器遥感超分辨率提供了有效轻量归纳偏置。源码见https://github.com/aminurhossain/SFG-SwinSR。
原文摘要 · Abstract (English)
Remote sensing single-image super-resolution aims to generate high-resolution imagery from low-resolution observations while preserving fine structures such as roads, building boundaries, field edges, and land-cover transitions. Swin Transformer-based models, including Swin2SR, provide strong spatial context modeling through shifted-window self-attention, but their feed-forward networks remain generic channelmixing modules that do not explicitly distinguish low-frequency structure from residual details. We propose SFG-SwinSR, which replaces the standard Swin2SR feed-forward network with a lightweight SpatialFrequency Gated Feed-Forward Network. The module estimates a smoothed feature component through a depthwise low-pass branch, derives residual details by subtraction, refines them spatially, and adaptively reinjects useful details through a bottleneck gate. Experiments on the real crosssensor SEN2VENμS, OLI2MSI, and SEN2NAIP benchmarks, together with an auxiliary synthetic SpaceNet Challenge 3 setting, show consistent improvements across most evaluation settings and competitive performance against recent Swin-based baselines. The results indicate that spatial-frequency transformation within transformer feed-forward networks provides an effective lightweight inductive bias for structure-aware cross-sensor remote sensing super-resolution. Source code is available at https://github.com/aminurhossain/SFG-SwinSR
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。