知识卡片
联合遮挡预测增加独立职责
网络可同时输出流与遮挡图,分别回答对应位移与该点是否在另一帧可见。遮挡标签需注明参考帧方向,并配置相应监督损失;把遮挡作为额外输出通道不代表其含义会在仅有流损失时自动被正确学出。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 学习运动估计
原书出处 · 1 处
- · 查看原书依据
One of the challenges for estimating optical flow is that, as objects move, they will occlude some pixels from the background and reveal new ones. Therefore, together with the estimated flow it is also convenient to detect occluded pixels. If we have ground truth data, we can train a function to estimate optical flow and the occlusion map from two frames:
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:摘录中关于联合遮挡预测增加独立职责的定义、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:One of the challenges for estimating optical flow is that, as objects move, they will occlude some pixels from the background and reveal new ones. Therefore, together with the estimated flow it is also convenient to detect occluded pixels. If we have ground truth data, we can train a function to estimate optical flow and the occlusion map from two frames: