Along the advanced progresses on deep neural networks, there are many impressive results on image inpainting. Several research works have tried to transfer successful experiences into image outpainting. Contextual attention net is one of the popular architectural units being applied to inpainting. We argue that it may be not suitable when embedded in an outpainting network. Instead, we adopt SEnet for it has global receptive field and channel-wise feature recalibration. This is very helpful for image outpainting. We also propose a non-fix local discriminator mechanism to decide whether a randomly select partial image is a real one. By ‘randomness’, the generator can produce a more realistic result. The experimental results are satisfactory and compatible to those on existing state-of-the-arts methods.
