将人工评测引入红外与可见光图像融合
Bridging Human Evaluation to Infrared and Visible Image Fusion
将人类主观偏好通过强化学习（GRPO）引入红外与可见光图像融合，提供了一套可复用的「人类反馈数据集构建+奖励模型训练+策略优化」范式，可迁移到其他低层视觉任务（如超分、去噪）以对齐人类感知。
原文依据 we propose a feedback reinforcement framework that bridges human evaluation to infrared and visible image fusion
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论红外与可见光图像融合（IVIF）整合互补模态以增强场景感知。当前方法主要关注优化手工设计的损失函数和客观指标，往往导致融合结果与人类视觉偏好不一致。IVIF 的病态性进一步加剧了这一挑战，严重限制了其在安防监控和驾驶辅助系统等人类感知环境中的有效性。为解决这些局限，我们提出了一种反馈强化框架，将人工评测引入红外与可见光图像融合。针对以人为中心的评估指标和数据的缺乏，我们构建了首个面向 IVIF 的大规模人类反馈数据集，包含多维主观评分和伪影标注，并通过微调的大语言模型结合专家审核进行丰富。基于该数据集，我们设计了一个领域特定的奖励函数并训练奖励模型以量化感知质量。在该奖励的引导下，我们通过组相对策略优化对融合网络进行微调，实现了最优性能，使融合图像更符合人类审美。代码见 https://github.com/ALKA-Wind/EVAFusion。
英文原文摘要 1284 字符
Infrared and visible image fusion (IVIF) integrates complementary modalities to enhance scene perception. Current methods predominantly focus on optimizing handcrafted losses and objective metrics, often resulting in fusion outcomes that do not align with human visual preferences. This challenge is further exacerbated by the ill-posed nature of IVIF, which severely limits its effectiveness in human perceptual environments such as security surveillance and driver assistance systems. To address these limitations, we propose a feedback reinforcement framework that bridges human evaluation to infrared and visible image fusion. To address the lack of human-centric evaluation metrics and data, we introduce the first large-scale human feedback dataset for IVIF, containing multidimensional subjective scores and artifact annotations, and enriched by a fine-tuned large language model with expert review. Based on this dataset, we design a domain-specific reward function and train a reward model to quantify perceptual quality. Guided by this reward, we fine-tune the fusion network through Group Relative Policy Optimization, achieving state-of-the-art performance that better aligns fused images with human aesthetics. Code is available at https://github.com/ALKA-Wind/EVAFusion.