论文标题
内在反射优化的不变描述符
Invariant Descriptors for Intrinsic Reflectance Optimization
论文作者
论文摘要
固有的图像分解旨在将图像分解为反照率（反射率）和阴影（照明）子组件。这是一个非常具有挑战性的计算机视觉问题。有无限的反射率和阴影图像可以重建相同的输入。为了解决该问题，野外的固有图像提供了一个基于密集的条件随机场（CRF）公式的优化框架，该框架考虑了远程材料关系。我们通过引入照明不变图像描述来改进它们的模型：颜色比率。颜色比率和反射率固有性都与照明不变，因此高度相关。通过详细的实验，我们提供了将颜色比率注入密集的CRF优化的方法。我们的方法是基于物理学的，无学习的，可导致更准确，更健壮的反射分解。
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 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 reflectance intrinsic 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, learning-free and leads to more accurate and robust reflectance decompositions.
