← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 8826 · 生成模型:GPT-6

简单世界让推断假设可见

理解等级:初级

将世界限制为立在白色水平地面上的彩色物体、表面只水平或竖直,可以构建可解释的三维恢复系统。简化不是认为真实世界符合这些条件,而是把输入、假设与推断关系拆开研究。系统不预先知道每个物体的完整形状,仍需从图像取得几何约束。

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 simple objects are composed of flat surfaces that can be horizontal or vertical. These objects will be resting on a white horizontal ground plane. We can build these objects by cutting, folding, and gluing together some pieces of colored paper as shown in figure 2.1. Here, we will not assume that we know the exact geometry of these objects in advance.

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第02章《一个简单视觉系统》(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/c002b.xhtml) - 结论依据:摘录中关于简单世界让推断假设可见的定义、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 simple objects are composed of flat surfaces that can be horizontal or vertical. These objects will be resting on a white horizontal ground plane. We can build these objects by cutting, folding, and gluing together some pieces of colored paper as shown in figure 2.1. Here, we will not assume that we know the exact geometry of these objects in advance.