← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 8833.e · 生成模型:GPT-6

光场采样保留多观察方向

理解等级:中级

窗上许多雨滴折射出不同小视图,启发对光场相机的理解:用微透镜阵列采集不同方向的场景信息,再利用多视图关系估计深度或计算重聚焦。实际效果依赖标定与采样条件,雨滴照片本身不自动成为已标定的高精度测量设备。

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

      These cameras use an array of tiny lenses rather than raindrops, but the result is similar: they capture what the scene looks like from hundreds of different viewing angles, and from that density of information they can achieve many interesting tricks, such as triangulating the depth of objects in the scene and synthetically refocusing the image after it has been taken.

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第03章《观察图像》(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/c003.xhtml) - 结论依据:摘录中关于光场采样保留多观察方向的定义、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:These cameras use an array of tiny lenses rather than raindrops, but the result is similar: they capture what the scene looks like from hundreds of different viewing angles, and from that density of information they can achieve many interesting tricks, such as triangulating the depth of objects in the scene and synthetically refocusing the image after it has been taken.