arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.02121cs.CVcs.GR
收藏

深度人像照明增强与3D指导

Deep Portrait Lighting Enhancement with 3D Guidance

City University of Hong Kong(香港城市大学)

Fangzhou Han, Can Wang, Hao Du, Jing Liao

摘要:

尽管用于图像光照增强的深度学习方法最近取得了突破,但它们在应用于肖像时表现较差,因为它们的模型中忽略了3D面部信息。为了解决这个问题,我们提出了一种新的深度学习框架,用于基于3D面部引导的人像照明增强。我们的框架包括两个阶段。在第一阶段中,通过网络从输入的不良照明图像预测校正的照明参数,在3D变形模型和可微分渲染器的帮助下。给定预测的光照参数,可微分渲染器渲染具有校正的阴影和纹理的人脸图像,其用作第二阶段中学习图像光照增强的3D指导。为了更好地利用输入和引导之间的远程相关性,在第二阶段,我们设计了一个具有新颖的Transformer架构的图像到图像转换网络,该网络自动产生照明增强的结果。在FFHQ数据集和野外图像上的实验结果表明,该方法在定量指标和视觉质量方面都优于现有的方法。我们将在https://cassiepython.github.io/egsr/index.html上发布我们的数据集以及更多结果。

英文摘要:

Despite recent breakthroughs in deep learning methods for image lighting enhancement, they are inferior when applied to portraits because 3D facial information is ignored in their models. To address this, we present a novel deep learning framework for portrait lighting enhancement based on 3D facial guidance. Our framework consists of two stages. In the first stage, corrected lighting parameters are predicted by a network from the input bad lighting image, with the assistance of a 3D morphable model and a differentiable renderer. Given the predicted lighting parameter, the differentiable renderer renders a face image with corrected shading and texture, which serves as the 3D guidance for learning image lighting enhancement in the second stage. To better exploit the long-range correlations between the input and the guidance, in the second stage, we design an image-to-image translation network with a novel transformer architecture, which automatically produces a lighting-enhanced result. Experimental results on the FFHQ dataset and in-the-wild images show that the proposed method outperforms state-of-the-art methods in terms of both quantitative metrics and visual quality. We will publish our dataset along with more results on https://cassiepython.github.io/egsr/index.html.

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。

↑