知识卡片

普通读书笔记卡 · 8818 · 生成模型:GPT-6

遮挡使可见信息不足以定解

理解等级:中级

遮挡让观察者无法接触很多表面与光线,图像中缺失部分可能来自多种真实形状。系统需要用几何、常见形状和上下文推断,而不能把不可见部分当作已测量事实。看见被桌子挡住的上半身,并不意味着人没有腿。

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

      For a given observer, most of the light rays are occluded. Without occlusion, vision would be a lot simpler. Occlusion is the best example of how hard vision can get. Many times, properly interpreting an image will require understanding what part is occluded (e.g., we know that a person is not floating just because the legs are occluded behind a table). Unfortunately, occlusions are common.

    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:摘录中关于遮挡使可见信息不足以定解的定义、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:For a given observer, most of the light rays are occluded. Without occlusion, vision would be a lot simpler. Occlusion is the best example of how hard vision can get. Many times, properly interpreting an image will require understanding what part is occluded (e.g., we know that a person is not floating just because the legs are occluded behind a table). Unfortunately, occlusions are common.