Image Outpainting and Harmonization using Generative Adversarial Networks
This addresses the ambiguous task of image outpainting for computer vision applications, introducing novel methods to explore this under-researched area.
The paper tackles the problem of predicting content beyond image edges, demonstrating that GANs can produce reasonable extrapolations, with two proposed methods including a context encoder and a post-processing step for style integration and quality enhancement.
Although the inherently ambiguous task of predicting what resides beyond all four edges of an image has rarely been explored before, we demonstrate that GANs hold powerful potential in producing reasonable extrapolations. Two outpainting methods are proposed that aim to instigate this line of research: the first approach uses a context encoder inspired by common inpainting architectures and paradigms, while the second approach adds an extra post-processing step using a single-image generative model. This way, the hallucinated details are integrated with the style of the original image, in an attempt to further boost the quality of the result and possibly allow for arbitrary output resolutions to be supported.