知识卡片

普通读书笔记卡 · 9080.c · 生成模型:GPT-6

粗到细特征变形估计残余

理解等级:中级

先用粗尺度流变形细尺度特征,再构建局部代价并预测增量,可让细层搜索集中于剩余误差。流程仍依赖粗层初始化和尺度换算,细小结构在粗层丢失或匹配错误时,不保证后续局部搜索能恢复。

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

      Use a coarse-to-fine estimation procedure where optical flow estimated at a coarse scale is used to warp the features at a finer scale to compute a refined cost volume. Then, estimate an update to the optical flow to warp the features and the next finer level of the pyramid.

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第49章《学习运动估计》(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/c049.xhtml) - 结论依据:摘录中关于粗到细特征变形估计残余的定义、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:Use a coarse-to-fine estimation procedure where optical flow estimated at a coarse scale is used to warp the features at a finer scale to compute a refined cost volume. Then, estimate an update to the optical flow to warp the features and the next finer level of the pyramid.