知识卡片

普通读书笔记卡 · 9044.d · 生成模型:GPT-6

大气透视只作条件性距离线索

理解等级:中级

远处山体的对比度可能因大气散射降低,雾会放大这一效应。对比度还受本身材质、光照、曝光等影响,所以低对比并不必然意味着更远。使用这类线索需要匹配环境条件和成像模型,不能把视觉色淡直接换成通用距离。

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

      When looking at large landscapes, like a mountain range, mountains that are far away have lower contrast due to dispersion by the atmosphere (see figure 43.1[b]). This effect gets accentuated when there is fog. Therefore, contrast can be used as a cue to infer relative distances between objects. This depth cue is called aerial perspective or atmospheric perspective. One example using haze to infer depth

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第43章《单图深度估计》(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/c043.xhtml) - 结论依据:摘录中关于大气透视只作条件性距离线索的定义、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:When looking at large landscapes, like a mountain range, mountains that are far away have lower contrast due to dispersion by the atmosphere (see figure 43.1[b]). This effect gets accentuated when there is fog. Therefore, contrast can be used as a cue to infer relative distances between objects. This depth cue is called aerial perspective or atmospheric perspective. One example using haze to infer depth