← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 9049.c · 生成模型:GPT-6

纯旋转视频不提供深度约束

理解等级:中级

同投影中心的纯旋转可用与深度无关的单应重建,因此再长的视频也不能靠这类重建唯一学出场景深度。需要产生视差的平移、足够纹理与可见结构。丰富运动有助于可辨识,但不能把帧数多直接当成几何信息足。

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

      As only the pixels with coordinates p′ inside the image can be reconstructed by warping, we compute the loss only over the valid set of pixels. This is done using the mask v (n, m), which is 1 for valid pixels and 0 for pixels that lie outside the visible part of the reference frame. The mask could also exclude pixels that fall in moving

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第43章《单图深度估计》(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/c043.xhtml) - 结论依据:摘录中关于纯旋转视频不提供深度约束的定义、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:As only the pixels with coordinates p′ inside the image can be reconstructed by warping, we compute the loss only over the valid set of pixels. This is done using the mask v (n, m), which is 1 for valid pixels and 0 for pixels that lie outside the visible part of the reference frame. The mask could also exclude pixels that fall in moving