Sketch-Guided Scenery Image Outpainting

TL;DR

This paper introduces a sketch-guided image outpainting method that allows users to customize generated scenery images by incorporating sketches, using alignment modules to ensure realism and consistency with user input.

Contribution

It presents the first approach to conditional scenery image outpainting guided by sketches, with a novel encoder-decoder network and alignment modules for improved realism and detail.

Findings

Outperforms state-of-the-art generative models in experiments

Effectively incorporates user sketches for personalized outpainting

Achieves high realism and consistency in generated images

Abstract

The outpainting results produced by existing approaches are often too random to meet users' requirement. In this work, we take the image outpainting one step forward by allowing users to harvest personal custom outpainting results using sketches as the guidance. To this end, we propose an encoder-decoder based network to conduct sketch-guided outpainting, where two alignment modules are adopted to impose the generated content to be realistic and consistent with the provided sketches. First, we apply a holistic alignment module to make the synthesized part be similar to the real one from the global view. Second, we reversely produce the sketches from the synthesized part and encourage them be consistent with the ground-truth ones using a sketch alignment module. In this way, the learned generator will be imposed to pay more attention to fine details and be sensitive to the guiding sketches. To our knowledge, this work is the first attempt to explore the challenging yet meaningful conditional scenery image outpainting. We conduct extensive experiments on two collected benchmarks to qualitatively and quantitatively validate the effectiveness of our approach compared with the other state-of-the-art generative models.