Illuminant Spectra-Based Source Separation Using Flash Photography
Illuminant Spectra-Based Source Separation Using Flash Photography
复制标题
DOI：
10.1109/cvpr.2018.00650
复制
发表时间：
2017-04
期刊：
影响因子：
--
通讯作者：
Zhuo Hui;Kalyan Sunkavalli;Sunil Hadap;Aswin C. Sankaranarayanan
中科院分区：
文献类型：
--
作者：
Zhuo Hui;Kalyan Sunkavalli;Sunil Hadap;Aswin C. Sankaranarayanan
真实世界中的照明通常由具有不同光谱的多个光源组成。在后处理中分离和操纵这些光源是一个具有挑战性的问题，需要大量的人工输入或校准场景几何和照明。在这项工作中，我们利用闪光灯/非闪光灯图像对根据它们的光谱差异来分析和编辑场景光源。我们推导出了一种新的基于物理的关系，在观察到的闪光/非闪光强度的颜色变化与对应于单个场景光源的光谱和表面阴影之间。我们的技术使用这种约束来自动将图像分离成由每个光源照亮的组成图像。这种分离可用于支持白平衡、照明编辑和RGB光度立体等应用，在这些应用中，我们展示了在各种图像上优于最先进技术的结果。
Real-world lighting often consists of multiple illuminants with different spectra. Separating and manipulating these illuminants in post-process is a challenging problem that requires either significant manual input or calibrated scene geometry and lighting. In this work, we leverage a flash/no-flash image pair to analyze and edit scene illuminants based on their spectral differences. We derive a novel physics-based relationship between color variations in the observed flash/no-flash intensities and the spectra and surface shading corresponding to individual scene illuminants. Our technique uses this constraint to automatically separate an image into constituent images lit by each illuminant. This separation can be used to support applications like white balancing, lighting editing, and RGB photometric stereo, where we demonstrate results that outperform state-of-the-art techniques on a wide range of images.