Painting Outside the Box: Image Outpainting with GANs
This addresses the under-explored task of image outpainting for computer vision applications, but it is incremental as it builds on existing methods like Iizuka et al.
The paper tackled the problem of image outpainting (extrapolation) by developing a deep learning approach using GANs, achieving relatively realistic outpainting of 128x128 color images and enabling recursive outpainting.
The challenging task of image outpainting (extrapolation) has received comparatively little attention in relation to its cousin, image inpainting (completion). Accordingly, we present a deep learning approach based on Iizuka et al. for adversarially training a network to hallucinate past image boundaries. We use a three-phase training schedule to stably train a DCGAN architecture on a subset of the Places365 dataset. In line with Iizuka et al., we also use local discriminators to enhance the quality of our output. Once trained, our model is able to outpaint $128 \times 128$ color images relatively realistically, thus allowing for recursive outpainting. Our results show that deep learning approaches to image outpainting are both feasible and promising.