知识卡片

普通读书笔记卡 · 9027.c · 生成模型:GPT-6

随机点立体图隔离视差线索

理解等级:中级

随机点立体图在单眼图中缺少可辨认物体,双眼融合后仍可看到相对位移构成的深度结构。它说明视差本身可提供深度线索,不依赖先识别语义对象;这并不表示人眼不使用其他单眼或运动线索。

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

      Our brain will use many different cues such as the ones presented in the previous chapter. But image disparity provides an independent additional cue. This is illustrated by the random dot stereograms (figure 40.3) introduced by Bela Julesz [241]. Random dot stereograms are a beautiful demonstration that humans can perceive depth using the relative displacement of features across two views even in the absence of

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第40章《立体视觉》(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/c040.xhtml) - 结论依据:摘录中关于随机点立体图隔离视差线索的定义、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:Our brain will use many different cues such as the ones presented in the previous chapter. But image disparity provides an independent additional cue. This is illustrated by the random dot stereograms (figure 40.3) introduced by Bela Julesz [241]. Random dot stereograms are a beautiful demonstration that humans can perceive depth using the relative displacement of features across two views even in the absence of