Painting Outside the Box: Image Outpainting with GANs

By Mark Sabini, Gili Rusak. 2018

83 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks (2021, background): “Other works address the so-called outpainting subtasks (Sabini & Rusak, 2018; Wang et al., 2019a; Yang et al., 2019b).”
COCO-GAN: Generation by Parts via Conditional Coordinating (2019, background): “In addition, the application is also similar to image restoration [14, 28, 29] or image out-painting [23].”
InfinityGAN: Towards Infinite-Resolution Image Synthesis (2021, background): “Image outpaint-ing [1, 18, 30, 40] is related to image inpainting [19, 41] and shares similar issues that the generator tends to copy-and-paraphrase the conditional input or create mottled textural samples, leading to repetitive results especially when the outpainted region is large.”