Learning physically based material and lighting decompositions for face editing  

作　　者：Qian Zhang Vikas Thamizharasan James Tompkin 

机构地区：[1]Brown University,Providence,Rhode Island 02906,USA

出　　处：《Computational Visual Media》2024年第2期295-308,共14页计算可视媒体（英文版）

基　　金：supported by NSF CAREER-2144956 and an Andy van Dam PhD Fellowship.

摘　　要：Lighting is crucial for portrait photography,yet the complex interactions between the skin and incident light are expensive to model computationally in graphics and difficult to reconstruct analytically via computer vision.Alternatively,to allow fast and controllable reflectance and lighting editing,we developed a physically based decomposition through deep learned priors from path-traced portrait images.Previous approaches that used simplified material models or low-frequency or low-dynamic-range lighting struggled to model specular reflections or relight directly without intermediate decomposition.However,we estimate the surface normal,skin albedo and roughness,and high-frequency HDRI maps,and propose an architecture to estimate both diffuse and specular reflectance components.In our experiments,we show that this approach can represent the true appearance function more effectively than simpler baseline methods,leading to better generalization and higher-quality editing.

关 键 词：intrinsic decomposition portrait relighting inverse rendering deep learning 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]