← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 8818.a · 生成模型:GPT-6

视觉错觉暴露场景解释机制

理解等级:中级

阴影中的格子与另一格可以具有相同像素强度,却被看成不同明度,因为视觉试图区分照明与表面反射。桌面错觉也显示二维形状受到三维解释影响。知道图像怎样构造未必能关闭这种自动感知,说明知觉并非简单光度计。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      The third example, figure 1.2(c), shows the “checkershadow illusion” by Adelson [11]. In this figure, the squares marked with A and B have the exact same intensity values. But the visual system is trying to measure the surface reflectance of the squares, removing the effect of the shadow to infer the true gray value of each square. As a result, the square in the shadow

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第01章《视觉的挑战》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c001.xhtml) - 结论依据:摘录中关于视觉错觉暴露场景解释机制的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:The third example, figure 1.2(c), shows the “checkershadow illusion” by Adelson [11]. In this figure, the squares marked with A and B have the exact same intensity values. But the visual system is trying to measure the surface reflectance of the squares, removing the effect of the shadow to infer the true gray value of each square. As a result, the square in the shadow