Bridging the Visual Gap: Wide-Range Image Blending

TL;DR

This paper introduces a deep learning approach for wide-range image blending, enabling smooth panoramic merging by generating intermediate content with high visual quality and semantic consistency.

Contribution

It proposes a novel Bidirectional Content Transfer module and combines attention and adversarial learning to improve wide-range image blending performance.

Findings

Produces visually appealing panoramic results

Outperforms state-of-the-art inpainting and outpainting baselines

Ensures semantic and spatial consistency

Abstract

In this paper we propose a new problem scenario in image processing, wide-range image blending, which aims to smoothly merge two different input photos into a panorama by generating novel image content for the intermediate region between them. Although such problem is closely related to the topics of image inpainting, image outpainting, and image blending, none of the approaches from these topics is able to easily address it. We introduce an effective deep-learning model to realize wide-range image blending, where a novel Bidirectional Content Transfer module is proposed to perform the conditional prediction for the feature representation of the intermediate region via recurrent neural networks. In addition to ensuring the spatial and semantic consistency during the blending, we also adopt the contextual attention mechanism as well as the adversarial learning scheme in our proposed method for improving the visual quality of the resultant panorama. We experimentally demonstrate that our proposed method is not only able to produce visually appealing results for wide-range image blending, but also able to provide superior performance with respect to several baselines built upon the state-of-the-art image inpainting and outpainting approaches.