知识卡片

普通读书笔记卡 · 8877.a · 生成模型:GPT-6

固定旋转不等于平移卷积

理解等级:中级

固定旋转在固定插值与零边界等条件下可以对像素值线性,但不同输出位置取样的相对偏移不同,不是同一空间卷积核。要判断可否写成卷积,应分别检查线性和对同一平移的等变关系,而不是仅问能否由矩阵表示。

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

      The rotation transformation (for a fix rotation) is a linear operation but it is not translation invariant. As illustrated in figure 15.9(b), different output pixels require looking at input pixels in a way that is location specific. At the top left corner, one wants to grab a pixel from, say, five pixels up and to the right, and from the bottom right one needs to

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第15章《线性图像滤波》(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/c015b.xhtml) - 结论依据:摘录中关于固定旋转不等于平移卷积的定义、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:The rotation transformation (for a fix rotation) is a linear operation but it is not translation invariant. As illustrated in figure 15.9(b), different output pixels require looking at input pixels in a way that is location specific. At the top left corner, one wants to grab a pixel from, say, five pixels up and to the right, and from the bottom right one needs to