Intrinsic image decomposition aims to factorize an image into albedo (reflectance) and shading (illumination) sub-components. Being ill posed and under-constrained, it is a very challenging computer vision problem. There are infinite pairs of reflectance and shading images that can reconstruct the same input. To address the problem, Intrinsic Images in the Wild by Bell et al. provides an optimization framework based on a dense conditional random field (CRF) formulation that considers long-range material relations. We improve upon their model by introducing illumination invariant image descriptors: color ratios. The color ratios and the intrinsic reflectance are both invariant to illumination and thus are highly correlated. Through detailed experiments, we provide ways to inject the color ratios into the dense CRF optimization. Our approach is physics based and learning free and leads to more accurate and robust reflectance decompositions.

中文翻译：

---

固有反射优化的不变描述符

内在图像分解旨在将图像分解为反照率（反射）和阴影（照明）子分量。由于身体不适和约束不足，这是一个非常具有挑战性的计算机视觉问题。有无数对反射和阴影图像可以重建相同的输入。为了解决这个问题，Bell等人的Intrinsic Images in the Wild. 提供了一个基于密集条件随机场 (CRF) 公式的优化框架，该公式考虑了远程材料关系。我们通过引入光照不变图像描述符来改进他们的模型：颜色比率。颜色比率和固有反射率都对光照是不变的，因此是高度相关的。通过详细的实验，我们提供了将颜色比率注入密集 CRF 优化的方法。我们的方法是基于物理学的，无需学习，可以实现更准确和更稳健的反射分解。