← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 9055.b · 生成模型:GPT-6

相机从光线形成图像

理解等级:中级

图像不是整个场的直接拷贝,而是相机通过光学系统与传感器对光线的采样和积分。针孔模型简化每像素的主要观察方向,真实曝光、像素面积与光圈仍引入积分效应。明确成像模型,才能把场景表示与训练像素正确连接。

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

      An image gets formed by summing all the light rays that reach each sensor on the camera (that is, we sum over a section of the plenoptic function). Figure 45.1 shows an illustration of the plenoptic function at four points, two of them are inside a pinhole camera and are used to form an image of what is outside. The plenoptic function inside the pinhole

    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:摘录中关于相机从光线形成图像的定义、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:An image gets formed by summing all the light rays that reach each sensor on the camera (that is, we sum over a section of the plenoptic function). Figure 45.1 shows an illustration of the plenoptic function at four points, two of them are inside a pinhole camera and are used to form an image of what is outside. The plenoptic function inside the pinhole