发表机构
Waseda University; The University of Tokyo; University of Amsterdam; Wuhan University; RIKEN（早稻田大学; 东京大学; 阿姆斯特丹大学; 武汉大学; 日本理化学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出EORestore-Agent智能体，通过视觉-语言模型报告残余退化、相对质量评分器预测PSNR/SSIM/LPIPS变化，实现无参考的逐步决策，在复合退化遥感图像上显著优于全能基线。
AI 中文摘要
遥感图像通常带有复合退化，其中雾、云、噪声、模糊、低光照和低分辨率同时存在。复原这些图像需要决定应用哪种工具、按什么顺序应用以及何时停止，然而在推理时没有干净的参考图像来验证这些决策。在单一退化上训练的全能模型随着退化累积会收敛到狭窄的PSNR区间。为了将真实世界的遥感复原表述为可追踪的轨迹，我们提出了EORestore-Agent，它用无参考、可验证的逐步决策替代了这一不可测量的目标。一个微调后的视觉-语言模型报告所有残余退化类型，其工具池被一起评分，因此复原顺序从逐步选择中涌现。一个相对质量评分器，在合成退化链上使用全参考监督进行训练，预测从当前图像到每个候选图像的PSNR、SSIM和LPIPS变化。只有当预测变化没有负值且预测PSNR增益为正时，步骤才被接受。否则，智能体保留当前图像。在包含六种退化类型的合成Landsat-8基准上，EORestore-Agent在二至六种退化的复合情况下，相比最强的重训练全能基线将PSNR提高了2.3至3.2 dB，而零样本自然图像智能体在18种设置中的17种中PSNR低于退化输入。用无参考质量差异替换学习评分器会损失1.1至4.6 dB。剩余的有害步骤很小且聚集在接受阈值附近。Sentinel-2示例展示了无需重训练即可迁移到真实大气退化。
英文摘要
Remote sensing images often carry composite degradations, in which haze, cloud, noise, blur, low light, and low resolution coexist. Restoring them requires deciding which tool to apply, in what order, and when to stop, yet no clean reference is available at inference time to verify these decisions. All-in-one models trained on single degradations converge to a narrow PSNR band as degradations accumulate. To formulate real-world remote sensing restoration as a traceable trajectory, we present EORestore-Agent, which replaces this unmeasurable objective with reference-free, verifiable per-step decisions. A fine-tuned vision-language model reports all residual degradation types, whose tool pools are scored together, so the restoration order emerges from step-wise selection. A relative quality scorer, trained with full-reference supervision on synthetic degradation chains, predicts the changes in PSNR, SSIM, and LPIPS from the current image to each candidate. A step is accepted only when no predicted change is negative and the predicted PSNR gain is positive. Otherwise, the agent keeps the current image. On a synthetic Landsat-8 benchmark with six degradation types, EORestore-Agent improves PSNR by 2.3 to 3.2 dB over the strongest retrained all-in-one baseline on composites of two to six degradations, whereas zero-shot natural-image agents fall below the degraded input in PSNR in 17 of 18 settings. Replacing the learned scorer with no-reference quality differences costs 1.1 to 4.6 dB. The remaining harmful steps are small and cluster near the acceptance threshold. Sentinel-2 examples illustrate transfer to real atmospheric degradation without retraining.
Comments20 pages, 6 figures, 11 tables, including appendices
