← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 8819.b · 生成模型:GPT-6

主动观察帮助识别稳定结构

理解等级:中级

主动改变视点使同一物体产生不同图像,观察者可借可控变化分辨稳定形状与投影差异。信息不仅存在于单帧,也存在于行动与连续观察的关系。这启发主动感知与自监督,但本章没有给出可直接替代所有几何学习的完整算法。

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

      we can get various images of a table in front of us simply by changing our position; and that we can sometimes have one view and sometimes another, just as we like at any time … Thus by our movements we find out that it is the stationary form of the table in space which is the cause of the changing image in our eyes.

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第01章《视觉的挑战》(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/c001.xhtml) - 结论依据:摘录中关于主动观察帮助识别稳定结构的定义、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:we can get various images of a table in front of us simply by changing our position; and that we can sometimes have one view and sometimes another, just as we like at any time … Thus by our movements we find out that it is the stationary form of the table in space which is the cause of the changing image in our eyes.