A robust multi-scale integration method to obtain the depth from gradient maps

作     者：Saracchini, Rafael F. V. Stolfi, Jorge Leitao, Helena C. G. Atkinson, Gary A. Smith, Melvyn L. 

作者机构：Univ Estadual Campinas Inst Comp Campinas SP Brazil Univ Fed Fluminense Inst Comp BR-24220000 Niteroi RJ Brazil Univ W England Machine Vis Lab Bristol BS16 1QY Avon England 

出 版 物：《COMPUTER VISION AND IMAGE UNDERSTANDING》 (计算机视觉与图像理解)

年 卷 期：2012年第116卷第8期

页      面：882-895页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Brazil's CNPq [301016/92-5, 550905/07-3] FAPESP [2007/59509-9, 2007/52015-0] CAPES [342109-0] UK EPSRC [EP/E028659/1] CnPQ EPSRC EPSRC [EP/I003061/1, EP/E028659/1] Funding Source: UKRI 

主　　题：Computer vision Multi-scale methods Gradient map integration Surface reconstruction 

摘      要：We describe a robust method for the recovery of the depth map (or height map) from a gradient map (or normal map) of a scene, such as would be obtained by photometric stereo or interferometry. Our method allows for uncertain or missing samples, which are often present in experimentally measured gradient maps, and also for sharp discontinuities in the scene s depth, e.g. along object silhouette edges. By using a multi-scale approach, our integration algorithm achieves linear time and memory costs. A key feature of our method is the allowance for a given weight map that flags unreliable or missing gradient samples. We also describe several integration methods from the literature that are commonly used for this task. Based on theoretical analysis and tests with various synthetic and measured gradient maps, we argue that our algorithm is as accurate as the best existing methods, handling incomplete data and discontinuities, and is more efficient in time and memory usage, especially for large gradient maps. (C) 2012 Elsevier Inc. All rights reserved.