Intensity-guided edge-preserving depth upsampling through weighted L0 gradient minimization

被引:8
作者
Jung, Cheolkon [1 ]
Yu, Shengtao [1 ]
Kim, Joongkyu [2 ]
机构
[1] Xidian Univ, Sch Elect Engn, Xian 710071, Peoples R China
[2] Sungkyunkwan Univ, Coll Informat & Commun Engn, Suwon 440746, South Korea
基金
中国国家自然科学基金;
关键词
Depth upsampling; Edge-preserving; Weighted L-0 sparsity; Alternating minimization; Half-quadratic splitting; SUPERRESOLUTION;
D O I
10.1016/j.jvcir.2016.11.009
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Depth is an important visual cue to perceive real-world scenes. Although a time-of-flight (ToF) depth camera can provide depth information in dynamic scenes, captured depth images are often noisy and of low resolution. In this paper, we propose an intensity-guided edge-preserving depth upsampling method through weighted L-0 gradient minimization to enhance both resolution and visual quality of depth images. Guided by the high-resolution intensity image, we perform optimization to preserve boundaries of objects. We apply L-0 gradient to the regularization term, and compute its weight from both intensity and depth images. We optimize the objective function using alternating minimization and half-quadratic splitting. Experimental results on Middlebury 2005, 2014, and real-world scene datasets demonstrate that the proposed method produces boundary-preserving depth upsampling results and outperforms state-of-the-art ones in terms of accuracy. (C) 2016 Elsevier Inc. All rights reserved.
引用
收藏
页码:132 / 144
页数:13
相关论文
共 57 条
[1]  
[Anonymous], 2004, 2004 C COMPUTER VISI
[2]  
[Anonymous], IEEE T IMAGE PROCESS
[3]  
[Anonymous], P IEEE ICIP
[4]  
[Anonymous], 2008, WORKSH MULT MULT SEN
[5]  
[Anonymous], P IEEE COMP SOC C CO
[6]  
[Anonymous], 2009, P VIS COMMUN IMAGE P
[7]  
[Anonymous], IEEE T IMAGE PROCESS
[8]  
[Anonymous], ACM T GRAPH
[9]  
[Anonymous], MULTIMED TOOLS APPL
[10]  
[Anonymous], P VIS COMM IM PROC V