视觉模型是否像人类一样感知静态图像中的错觉运动？
Do vision models perceive illusory motion in static images like humans?
AI总结：
研究评估了多种光流模型在Rotating Snakes illusion中的表现，发现大多数模型无法生成与人类感知一致的流场，仅人类启发的Dual-Channel模型在模拟眼跳条件下表现出预期的旋转运动。
摘要：
理解人类运动处理对于构建可靠的人机计算机视觉系统至关重要。尽管深度神经网络（DNN）在光流估计中表现优异，但其鲁棒性仍不及人类，且依赖于不同的计算策略。视觉运动错觉为探索这些机制提供了有力工具，揭示了人类和机器视觉的相似性与差异。尽管最近的DNN基于运动模型可以重现动态错觉如反向-phi，但尚不清楚它们是否能感知静态图像中的错觉运动，例如旋转蛇错觉。我们评估了几种代表性的光流模型在旋转蛇错觉中的表现，并展示大多数模型无法生成与人类感知一致的流场。在模拟条件下模仿眼跳运动时，只有人类启发的Dual-Channel模型表现出预期的旋转运动，最接近的对应关系出现在眼跳模拟期间。消融分析进一步揭示了基于亮度和更高阶颜色-特征-基于的运动信号对这种行为的贡献，并且递归注意力机制对于整合局部线索至关重要。我们的结果强调了当前光流模型与人类视觉运动处理之间存在显著差距，并为开发具有改进对应关系的人类感知和人本AI的未来运动估计系统提供了见解。
英文摘要：
Understanding human motion processing is essential for building reliable, human-centered computer vision systems. Although deep neural networks (DNNs) achieve strong performance in optical flow estimation, they remain less robust than humans and rely on fundamentally different computational strategies. Visual motion illusions provide a powerful probe into these mechanisms, revealing how human and machine vision align or diverge. While recent DNN-based motion models can reproduce dynamic illusions such as reverse-phi, it remains unclear whether they can perceive illusory motion in static images, exemplified by the Rotating Snakes illusion. We evaluate several representative optical flow models on Rotating Snakes and show that most fail to generate flow fields consistent with human perception. Under simulated conditions mimicking saccadic eye movements, only the human-inspired Dual-Channel model exhibits the expected rotational motion, with the closest correspondence emerging during the saccade simulation. Ablation analyses further reveal that both luminance-based and higher-order color--feature--based motion signals contribute to this behavior and that a recurrent attention mechanism is critical for integrating local cues. Our results highlight a substantial gap between current optical-flow models and human visual motion processing, and offer insights for developing future motion-estimation systems with improved correspondence to human perception and human-centric AI.
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。
