基于卷积核合成的框架
卷积核同时考虑运动估计和 re-sampling。 对于 large motion,就需要 large kernels。
输出 两个 41×41 kernels,对于一张 1080p 图像的合成, the output kernels alone will require 26 GB of memory
当我们采用了separable convolution, For a 1080p video frame, using separable kernels that approximate 41 × 41 ones only requires 1.27 GB
Loss function 这里我们考虑两类损失函数:第一类是 L1 per-pixel color difference,第二类 L_F loss functions that this work explores is perceptual loss, which has often been found effective in producing visually pleasing images