Boundless: Generative Adversarial Networks for Image Extension

TL;DR

This paper introduces a GAN-based method with semantic conditioning for high-quality image extension, producing coherent, visually appealing results even in extreme cases like panoramas.

Contribution

It presents a novel semantic conditioning approach in GAN discriminators specifically designed for image extension tasks, outperforming existing inpainting methods.

Findings

Achieves coherent and visually pleasing extended images.

Effective in extreme cases like panorama generation.

Outperforms traditional inpainting techniques in quality.

Abstract

Image extension models have broad applications in image editing, computational photography and computer graphics. While image inpainting has been extensively studied in the literature, it is challenging to directly apply the state-of-the-art inpainting methods to image extension as they tend to generate blurry or repetitive pixels with inconsistent semantics. We introduce semantic conditioning to the discriminator of a generative adversarial network (GAN), and achieve strong results on image extension with coherent semantics and visually pleasing colors and textures. We also show promising results in extreme extensions, such as panorama generation.