Bridging the Visual Gap: Wide-Range Image Blending
This addresses a novel problem in image processing for creating seamless panoramas, but it appears incremental as it builds on existing techniques like inpainting and outpainting.
The paper tackles the problem of wide-range image blending, which merges two different photos into a panorama by generating novel content for the intermediate region, and demonstrates that their method produces visually appealing results with superior performance over state-of-the-art baselines.
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.