← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 9082.b · 生成模型:GPT-6

光度误差不唯一识别真实流

理解等级:中级

重复纹理、均匀区域及照明变化可使多种位移有相近重建误差。L1或稳健范数降低大残差支配,却不自动解决对应歧义与遮挡;应结合其他约束和独立运动评价,不能只凭低光度损失宣称真值恢复。

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:摘录中关于光度误差不唯一识别真实流的定义、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.