Deep Neural Models for Illumination Estimation and Relighting: A Survey
Deep Neural Models for Illumination Estimation and Relighting: A Survey
复制标题
DOI：
10.1111/cgf.14283
复制
发表时间：
2021-06
影响因子：
2.5
通讯作者：
Farshad Einabadi;Jean-Yves Guillemaut;A. Hilton
中科院分区：
文献类型：
--
作者：
Farshad Einabadi;Jean-Yves Guillemaut;A. Hilton
在混合现实场景中，场景重照明和估计真实场景的照明以插入虚拟物体是计算机视觉和图形学领域中研究得很好的挑战。经典的反向渲染方法旨在将场景分解为其正交的构成元素，即场景几何、照明和表面材料，这些元素可用于增强现实或在新的照明或视点下渲染新图像。近年来，深度神经计算在照明估计、重光照和逆向渲染等方面的应用取得了良好的效果。这项贡献旨在以连贯的方式汇集这一领域的最新进展。我们详细研究了所提出方法的属性，分为三类：场景照明估计，具有反射感知的场景特定表示的重照明，最后作为图像到图像转换的重照明。每一类最后都讨论了当前方法的主要特点和可能的未来趋势。我们还提供了神经照明应用的当前公开可用数据集的概述。
Scene relighting and estimating illumination of a real scene for insertion of virtual objects in a mixed‐reality scenario are well‐studied challenges in the computer vision and graphics fields. Classical inverse rendering approaches aim to decompose a scene into its orthogonal constituting elements, namely scene geometry, illumination and surface materials, which can later be used for augmented reality or to render new images under novel lighting or viewpoints. Recently, the application of deep neural computing to illumination estimation, relighting and inverse rendering has shown promising results. This contribution aims to bring together in a coherent manner current advances in this conjunction. We examine in detail the attributes of the proposed approaches, presented in three categories: scene illumination estimation, relighting with reflectance‐aware scene‐specific representations and finally relighting as image‐to‐image transformations. Each category is concluded with a discussion on the main characteristics of the current methods and possible future trends. We also provide an overview of current publicly available datasets for neural lighting applications.