欺骗的艺术：色彩视觉错觉与扩散模型
The Art of Deception: Color Visual Illusions and Diffusion Models
AI总结：
本研究探究视觉错觉在扩散模型中的编码机制，发现其潜在空间存在类人亮度/色彩偏移，可预测视觉错觉，还能利用文本到图像扩散模型生成新型错觉，且经心理物理学实验验证该类错觉可欺骗人类。
摘要：
人类的视觉错觉产生于对分布外刺激的解读过程中：如果观察者适应了特定的统计规律，对异常值的感知就会偏离现实。近期研究表明，人工神经网络（ANNs）也会被视觉错觉欺骗。这一发现引发了关于视觉信息本质的深刻问题：为何人脑与人工神经网络这两个独立系统会受相同错觉的影响？是否所有人工神经网络都能感知视觉错觉？这类感知是一种特性还是缺陷？在本研究中，我们探究了视觉错觉在扩散模型中的编码方式。值得注意的是，我们发现扩散模型的潜在空间中存在类人的亮度/色彩偏移。我们利用这一特性证明了扩散模型能够预测视觉错觉。此外，我们还展示了如何利用文本到图像的扩散模型在真实感图像中生成前所未见的新型视觉错觉。我们通过心理物理学实验验证了这一能力，结果表明我们的模型生成的错觉同样能骗过人类。
英文摘要：
Visual illusions in humans arise when interpreting out-of-distribution stimuli: if the observer is adapted to certain statistics, perception of outliers deviates from reality. Recent studies have shown that artificial neural networks (ANNs) can also be deceived by visual illusions. This revelation raises profound questions about the nature of visual information. Why are two independent systems, both human brains and ANNs, susceptible to the same illusions? Should any ANN be capable of perceiving visual illusions? Are these perceptions a feature or a flaw? In this work, we study how visual illusions are encoded in diffusion models. Remarkably, we show that they present human-like brightness/color shifts in their latent space. We use this fact to demonstrate that diffusion models can predict visual illusions. Furthermore, we also show how to generate new unseen visual illusions in realistic images using text-to-image diffusion models. We validate this ability through psychophysical experiments that show how our model-generated illusions also fool humans.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
