← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 9063.b · 生成模型:GPT-6

光流与立体共享匹配问题

理解等级:中级

两帧运动估计和立体视差都寻找对应位置,但静态场景立体有相机几何提供的极线约束。一般动态场景不能直接使用一组静态极线解释所有点;校正立体的垂直视差为零是特定几何条件下的结果。

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

      Motion estimation between two frames in a sequence is closely related to disparity estimation in stereo images. A key difference is that stereo images incorporate additional constraints, as only the camera moves—imagine a stereo pair as a sequence with a moving camera while everything else remains static. The displacements between stereo images respect the epipolar constraint, which allows the estimated motions to be more robust.

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第46章《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/c046b.xhtml) - 结论依据:摘录中关于光流与立体共享匹配问题的定义、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:Motion estimation between two frames in a sequence is closely related to disparity estimation in stereo images. A key difference is that stereo images incorporate additional constraints, as only the camera moves—imagine a stereo pair as a sequence with a moving camera while everything else remains static. The displacements between stereo images respect the epipolar constraint, which allows the estimated motions to be more robust.