← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 8924.a · 生成模型:GPT-6

拉普拉斯层存预测残差

理解等级:中级

先将粗层gₖ₊₁通过固定扩展算子Fₖ恢复到细层大小,再定义lₖ=gₖ−Fₖgₖ₊₁。它保存粗层预测不了的细节,而不是简单对每层应用五点拉普拉斯。差值有正有负,需要保留符号与精度;显示成灰底图不代表它只有非负像素。

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

      In the Gaussian pyramid, each level losses some of the fine image details available in the previous level. The Laplacian pyramid [66] is simple: it represents, at each level, what is present in a Gaussian pyramid image of one level, but not present at the level below it. We calculate that by expanding the lower-resolution Gaussian pyramid image to the same pixel resolution as the

    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:摘录中关于拉普拉斯层存预测残差的定义、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:In the Gaussian pyramid, each level losses some of the fine image details available in the previous level. The Laplacian pyramid [66] is simple: it represents, at each level, what is present in a Gaussian pyramid image of one level, but not present at the level below it. We calculate that by expanding the lower-resolution Gaussian pyramid image to the same pixel resolution as the