← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 9059.c · 生成模型:GPT-6

体渲染并非完整光传输

理解等级:中级

本章体渲染把沿射线的有效颜色按吸收与透射累积,能表达半透明外观。它没有因此自动模拟物理折射、次表面散射和任意多次反射;这些效果若出现在训练图中,往往被烘焙到所拟合的外观,而非显式求解。

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

      This is all to say that volume rendering is a simple generalization of ray casting. One advantage it has is that it can model translucency, and media like gases, fluids, and thin films that let some photons pass through and reflect back others. We will see an even bigger advantage in section 45.5, where we will find that volume rendering gives good gradients for fitting

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第45章《辐射场》(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/c045.xhtml) - 结论依据:摘录中关于体渲染并非完整光传输的定义、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:This is all to say that volume rendering is a simple generalization of ray casting. One advantage it has is that it can model translucency, and media like gases, fluids, and thin films that let some photons pass through and reflect back others. We will see an even bigger advantage in section 45.5, where we will find that volume rendering gives good gradients for fitting