Intrinsic image estimation using near- \(L_0\) sparse optimization

详细信息    查看全文

• 作者：Shouhong Ding ; Bin Sheng ; Zhifeng Xie ; Lizhuang Ma
• 关键词：Intrinsic image decomposition ; Reflectance ; Shading ; \(L_0\) ; sparsity
• 刊名：The Visual Computer
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：33
• 期：3
• 页码：355-369
• 全文大小：
• 刊物类别：Computer Science
• 刊物主题：Computer Graphics; Computer Science, general; Artificial Intelligence (incl. Robotics); Image Processing and Computer Vision;
• 出版者：Springer Berlin Heidelberg
• ISSN：1432-2315
• 卷排序：33

文摘

The objective of intrinsic images estimation is to decompose an input image into its intrinsic shading and reflectance components. This is a well-known under-constrained problem that has long been an open challenge. This paper proposes a novel approach for automatic intrinsic images decomposition that uses a new reflectance sparsity prior. On the basis of the observation that the reflectance of natural objects is commonly piecewise constant, we formalize this constraint on the entire reflectance image using the \(L_0\) sparse loss function that enforces the variation in reflectance images to be of high-frequency and sparse. This new sparsity constraint significantly improves the quality of Retinex intrinsic images estimation. It also functions effectively by combining a class of global sparsity priors on reflectance. Experimental results on MIT benchmark dataset as well as various real-world images and synthetic images demonstrate the effectiveness and versatility of our approach.