Zhan Fangneng, Yu Yingchen, Zhang Changgong, Wu Rongliang, Hu Wenbo, Lu Shijian, Ma Feiying, Xie Xuansong, Shao Ling
IEEE Trans Image Process. 2022;31:2268-2278. doi: 10.1109/TIP.2022.3151997. Epub 2022 Mar 11.
Inferring the scene illumination from a single image is an essential yet challenging task in computer vision and computer graphics. Existing works estimate lighting by regressing representative illumination parameters or generating illumination maps directly. However, these methods often suffer from poor accuracy and generalization. This paper presents Geometric Mover's Light (GMLight), a lighting estimation framework that employs a regression network and a generative projector for effective illumination estimation. We parameterize illumination scenes in terms of the geometric light distribution, light intensity, ambient term, and auxiliary depth, which can be estimated by a regression network. Inspired by the earth mover's distance, we design a novel geometric mover's loss to guide the accurate regression of light distribution parameters. With the estimated light parameters, the generative projector synthesizes panoramic illumination maps with realistic appearance and high-frequency details. Extensive experiments show that GMLight achieves accurate illumination estimation and superior fidelity in relighting for 3D object insertion. The codes are available at https://github.com/fnzhan/Illumination-Estimation.
从单张图像推断场景光照是计算机视觉和计算机图形学中一项重要但具有挑战性的任务。现有工作通过回归代表性光照参数或直接生成光照图来估计光照。然而，这些方法往往存在精度差和泛化能力弱的问题。本文提出了几何移动光（GMLight），这是一种光照估计框架，它采用回归网络和生成投影仪进行有效的光照估计。我们根据几何光分布、光强度、环境项和辅助深度来参数化光照场景，这些可以通过回归网络进行估计。受推土机距离的启发，我们设计了一种新颖的几何移动损失来指导光分布参数的精确回归。利用估计的光照参数，生成投影仪合成具有逼真外观和高频细节的全景光照图。大量实验表明，GMLight在3D物体插入的重光照中实现了准确的光照估计和卓越的逼真度。代码可在https://github.com/fnzhan/Illumination-Estimation获取。
