Chen Xi, Zhu Weixin, Zhao Yang, Yu Yao, Zhou Yu, Yue Tao, Du Sidan, Cao Xun
Appl Opt. 2017 Jul 10;56(20):5676-5684. doi: 10.1364/AO.56.005676.
In this paper, we present a spectral intrinsic image decomposition (SIID) model, which is dedicated to resolve a natural scene into its purely independent intrinsic components: illumination, shading, and reflectance. By introducing spectral information, our work can solve many challenging cases, such as scenes with metameric effects, which are hard to tackle for trichromatic intrinsic image decomposition (IID), and thus offers potential benefits to many higher-level vision tasks, e.g., materials classification and recognition, shape-from-shading, and spectral image relighting. A both effective and efficient algorithm is presented to decompose a spectral image into its independent intrinsic components. To facilitate future SIID research, we present a public dataset with ground-truth illumination, shading, reflectance and specularity, and a meaningful error metric, so that the quantitative comparison becomes achievable. The experiments on this dataset and other images demonstrate the accuracy and robustness of the proposed method on diverse scenes, and reveal that more spectral channels indeed facilitate the vision task (i.e., segmentation and recognition).
在本文中，我们提出了一种光谱内在图像分解（SIID）模型，该模型致力于将自然场景分解为其完全独立的内在成分：光照、阴影和反射率。通过引入光谱信息，我们的工作可以解决许多具有挑战性的情况，例如具有同色异谱效应的场景，这对于三色内在图像分解（IID）来说很难处理，因此为许多高级视觉任务提供了潜在的好处，例如材料分类与识别、从阴影恢复形状以及光谱图像重光照。我们提出了一种既有效又高效的算法，用于将光谱图像分解为其独立的内在成分。为了促进未来的SIID研究，我们提供了一个包含真实光照、阴影、反射率和镜面反射的公共数据集，以及一个有意义的误差度量，从而实现定量比较。在这个数据集和其他图像上进行的实验证明了所提出方法在不同场景下的准确性和鲁棒性，并揭示了更多的光谱通道确实有助于视觉任务（即分割和识别）。
