发表机构
University of Rochester（罗切斯特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出多维观察者模型，将图像表示为潜在感知空间分布，以理解人类图像质量判断，发现感知空间维度极低且结构随任务变化。
AI 中文摘要
判断图像质量不仅与人类日常任务的生态相关性密切相关，而且支撑着图像生成等许多机器视觉任务。本文提出了一个框架来理解人类图像质量判断背后的固有感知空间。我们提出了一种多维观察者模型，该模型将图像表示为潜在感知空间中的分布，并将人类判断建模为对噪声样本的比较。该模型受灵长类动物腹侧流神经表征的约束，并拟合大规模行为数据，能够在匹配现有指标预测能力的同时分析感知结构。利用该模型，我们发现，即使考虑到图像空间的稀疏性，解释人类图像质量判断所需的感知空间相对于图像空间而言维度极低。该空间的具体结构（如维度、编码信息）在低级和高级质量判断之间有所不同，这表明尽管在开始时存在共享的视网膜编码，但人类在视觉决策中选择性地构建任务相关的感知空间。
英文摘要
Judging image quality is not only ecologically relevant to everyday human tasks, but also underpins many machine vision tasks such as image generation. This paper proposes a framework to understand the inherent perceptual space underlying image quality judgment in humans. We propose a multi-dimensional observer model that represents images as distributions in a latent perceptual space and that models human judgment as comparing noisy samples. Being constrained by neural representations in the primate ventral stream and fit to large-scale behavioral data, the model enables analysis of perceptual structure while matching the predictive power of existing metrics. Using this model, we find that the perceptual spaces needed to account for image quality judgment in humans are extremely low-dimensional compared to the image space even when considering its sparsity. The exact structure of the space (e.g., dimensionalities, information encoded) varies between low-level and high-level quality judgments, suggesting that, despite a shared retinal encoding in the beginning, humans selectively construct task-dependent perceptual spaces in visual decision making.
CommentsAccepted at NeurIPS 2026. 25 pages
