3D-aware portrait lighting control is an emerging and promising domain, thanks to the recent
advance of generative adversarial networks and neural radiance fields. Existing solutions …

In this paper, we present an end-to-end neural solution to model portrait bas-relief from a
single photograph, which is cast as a problem of image-to-depth translation. The main …

Portrait viewpoint and illumination editing is an important problem with several applications
in VR/AR, movies, and photography. Comprehensive knowledge of geometry and …

3D reconstruction from a single RGB image is a challenging problem in computer vision.
Previous methods are usually solely data-driven, which lead to inaccurate 3D shape …

Images recorded during the lifetime of computer vision based systems undergo a wide
range of illumination and environmental conditions affecting the reliability of previously …

In-the-wild face photographs often suffer from undesirable foreign shadows cast by external
objects (eg hands, phones, and trees). Removing facial foreign shadows not only improves …

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 …

We develop a new method for portrait image editing, which supports fine-grained editing of
geometries, colors, lights and shadows using a single neural network model. We adopt a …

摘要欠曝光图像的增强在很多研究领域都有重要意义. 在本文中, 我们把此问题视为欠曝光图像
与其成对增强版本之间的图像特征变换, 并针对该问题提出了一种深度对称网络 …

The field of face recognition sees a lot of development, but its use in forensic settings has
lagged behind. One of the reasons for this is the lack of face image sets of sufficient size for …