← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 9082.a · 生成模型:GPT-6

可微变形传递光度梯度

理解等级:中级

网络预测前向流后,可在第二帧p+f(p)处采样,与第一帧p的颜色比较并对网络参数反传。需要连续插值与有效掩码。正文说warp第一帧重建第二帧,而式49.4实际按第二帧采样重建第一帧,使用时应依公式明确方向。

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

      The learning is done by searching over the parameter space for the parameters θ that minimize the photometric loss over a large collection of videos. The photometric loss can also be replaced by the L1 or other robust norms. If the network also predicts occlusions, the photometric loss can include a weight that cancels the contribution of occluded pixels to the loss.

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第49章《学习运动估计》(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/c049.xhtml) - 结论依据:摘录中关于可微变形传递光度梯度的定义、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:The learning is done by searching over the parameter space for the parameters θ that minimize the photometric loss over a large collection of videos. The photometric loss can also be replaced by the L1 or other robust norms. If the network also predicts occlusions, the photometric loss can include a weight that cancels the contribution of occluded pixels to the loss.