当前位置 >>成果展示 >>论文

Depth Super-Resolution via Joint Color-Guided Internal and External Regularizations.(IEEE Transactions on Image Processing 2019)时间: 2019-04-01 点击: 123 次


作者:Liu, XM (Liu, Xianming)[ 1,2 ] ; Zhai, DM (Zhai, Deming)[ 1,2 ] ; Chen, R (Chen, Rong)[ 1 ] ; Ji, XY (Ji, Xiangyang)[ 3 ] ; Zhao, DB (Zhao, Debin)[ 1,2 ] ; Gao, W (Gao, Wen)[ 2,4




IEEE TRANSACTIONS ON IMAGE PROCESSING

卷: 28

期: 4

页: 1636-1645

DOI: 10.1109/TIP.2018.2875506

出版年: APR 2019

文献类型:Article



摘要

Depth information is being widely used in many real-world applications. However, due to the limitation of depth sensing technology, the captured depth map in practice usually has much lower resolution than that of color image counterpart. In this paper, we propose to combine the internal smoothness prior and external gradient consistency constraint in graph domain for depth super-resolution. On one hand, a new graph Laplacian regularizer is proposed to preserve the inherent piecewise smooth characteristic of depth, which has desirable filtering properties. A specific weight matrix of the respect graph is defined to make full use of information of both depth and the corresponding guidance image. On the other hand, inspired by an observation that the gradient of depth is small except at edge separating regions, we introduce a graph gradient consistency constraint to enforce that the graph gradient of depth is close to the thresholded gradient of guidance. We reinterpret the gradient thresholding model as variational optimization with sparsity constraint. In this way, we remedy the problem of structure discrepancy between depth and guidance. Finally, the internal and external regularizations are casted into a unified optimization framework, which can be efficiently addressed by ADMM. Experimental results demonstrate that our method outperforms the state-of-the-art with respect to both objective and subjective quality evaluations.


基金资助致谢
基金资助机构显示详情 授权号
2015CB351804
61672193
61502122
61620106005
HIT. NSRIF. 2015067
Tsinghua University Initiative Scientific Research Program   


上一篇:Optimize x265 Rate Control: An Exploration of Lookahead in Frame Bit Allocation and Slice Type Decis.(IEEE Transactions on Image Processing 2019) 下一篇:Graph-Based Joint Dequantization and Contrast Enhancement of Poorly Lit JPEG Images.(IEEE Transactions on Image Processing 2019) 返回列表

用户登录

用户注册