Automatic Contextual Cropping And

Free-Form Image Inpainting With Gated Convolution

cies, contextual attention module [49] is proposed and inte-grated into networks to explicitly borrow information from distant spatial locations. However, this approach is mainly trained on large rectangular masks and does not generalize well on free-form masks. To better handle irregular masks, partial convolution [23] is proposed where the ...

  With, Image, Convolutions, Contextual, Gated, Inpainting, Image inpainting with gated convolution