知识卡片

普通读书笔记卡 · 8925.a · 生成模型:GPT-6

融合掩膜使用高斯金字塔

理解等级:中级

两幅源图分别建立Laplacian金字塔,掩膜建立Gaussian金字塔。在每一对应尺度按mₖ混合源图细节:lₖ=mₖlₖᴬ+(1−mₖ)lₖᴮ;最粗低通残差也做同样融合,最后从粗到细合成。每个mₖ必须与相应图层尺寸一致。

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

      Using the Laplacian pyramid, we can transition from one image to the next over many different spatial scales to make a gradual transition between the two images. The algorithm proceeds as follows. We first build the Laplacian pyramid for the two input images; in this example we use seven levels and we also keep the last low-pass residual as shown in figure 23.8.

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第23章《图像金字塔》(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/c023.xhtml) - 结论依据:摘录中关于融合掩膜使用高斯金字塔的定义、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:Using the Laplacian pyramid, we can transition from one image to the next over many different spatial scales to make a gradual transition between the two images. The algorithm proceeds as follows. We first build the Laplacian pyramid for the two input images; in this example we use seven levels and we also keep the last low-pass residual as shown in figure 23.8.