语义色彩自然度破坏器：通过内容感知颜色先验防止非法图像上色
Semantic Color Naturalness Breaker: Preventing Illegitimate Colorization via Content-Aware Color Priors
浏览论文内容
中文总结 AI 辅助
研究如何防止灰度图像非法上色，提出语义色彩自然度破坏器SCNB框架，利用内容感知颜色分布距离CaCDD，在保持灰度媒体视觉保真度时使上色输出偏向与内容不一致颜色，实验表明该方法在实际场景中有效。
中文摘要 AI 辅助
自动图像上色能够大规模、低成本地重新利用灰度媒体，但这也便利了未经授权的再利用和重新分发。基于不可上色示例（UE），我们提出语义色彩自然度破坏器（SCNB），这是一个语义级UE框架，能在保持灰度媒体视觉保真度的同时，使上色输出偏向与内容不一致的颜色。我们还引入了内容感知颜色分布距离（CaCDD），它无需真实数据，基于语义颜色先验得出，用作SCNB的优化目标和评估指标。在ImageNet上的实验表明，该方法在小扰动预算和常见后处理下仍有效，支持在实际内容共享管道中部署。
英文摘要
Automatic image colorization enables large-scale and low-cost reuse of grayscale media (e.g., manga panels and archival photographs), facilitating unauthorized reuse and redistribution. Once released online, grayscale content can be readily turned into unauthorized colorized derivatives using off-the-shelf models, creating a practical need for proactive, content-side protection at publication time. Building on Uncolorable Examples (UE), which add imperceptible perturbations to released grayscale images to degrade unauthorized colorization, we propose Semantic Color Naturalness Breaker (SCNB) -- a semantic-level UE framework that drives colorization outputs toward content-inconsistent colors while preserving the visual fidelity of the released grayscale media. We further introduce Content-aware Color Distributional Distance (CaCDD), a ground-truth-free, content-aware measure of color plausibility derived from semantic color priors, used both as the optimization objective of SCNB and as an evaluation metric. Experiments on ImageNet show that our method remains effective under small perturbation budgets and common post-processing, supporting practical deployment in real-world content-sharing pipelines.
发表机构
- The University of Tokyo（东京大学）
- National Institute of Informatics（国立情报学研究所）
机构由 AI 辅助整理，请以论文原文为准。
