基于深度结构模型的广角人像校正
Practical Wide-Angle Portraits Correction with Deep Structured Models
摘要：
广角肖像往往享有扩大的意见。然而，它们包含透视失真，在拍摄团体肖像照片时尤其明显，其中背景倾斜，面部拉伸。本文介绍了第一种基于深度学习的方法，用于从自由拍摄的照片中去除此类伪影。具体来说，给定一个广角肖像作为输入，我们建立了一个级联网络，由LineNet，ShapeNet和过渡模块（TM）组成，该模块校正背景上的透视失真，适应面部区域上的立体投影，并相应地实现这两个投影之间的平滑过渡。为了训练我们的网络，我们构建了第一个透视人像数据集，其中包含身份、场景和相机模块的大量多样性。对于定量评价，我们引入了两个新的指标，线一致性和脸一致性。与以前的最先进的方法相比，我们的方法不需要相机失真参数。我们证明，我们的方法显着优于以前的国家的最先进的方法在定性和定量。
英文摘要：
Wide-angle portraits often enjoy expanded views. However, they contain perspective distortions, especially noticeable when capturing group portrait photos, where the background is skewed and faces are stretched. This paper introduces the first deep learning based approach to remove such artifacts from freely-shot photos. Specifically, given a wide-angle portrait as input, we build a cascaded network consisting of a LineNet, a ShapeNet, and a transition module (TM), which corrects perspective distortions on the background, adapts to the stereographic projection on facial regions, and achieves smooth transitions between these two projections, accordingly. To train our network, we build the first perspective portrait dataset with a large diversity in identities, scenes and camera modules. For the quantitative evaluation, we introduce two novel metrics, line consistency and face congruence. Compared to the previous state-of-the-art approach, our method does not require camera distortion parameters. We demonstrate that our approach significantly outperforms the previous state-of-the-art approach both qualitatively and quantitatively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
