Jin Wu, Zun Li, Yong Liu
School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China.
School of Physics and Electronic Engineering, Xinxiang College, Xinxiang 453000, China.
Sensors (Basel). 2020 Mar 24;20(6):1797. doi: 10.3390/s20061797.
In real applications, obtained depth images are incomplete; therefore, depth image inpainting is studied here. A novel model that is characterised by both a low-rank structure and nonlocal self-similarity is proposed. As a double constraint, the low-rank structure and nonlocal self-similarity can fully exploit the features of single-depth images to complete the inpainting task. First, according to the characteristics of pixel values, we divide the image into blocks, and similar block groups and three-dimensional arrangements are then formed. Then, the variable splitting technique is applied to effectively divide the inpainting problem into the sub-problems of the low-rank constraint and nonlocal self-similarity constraint. Finally, different strategies are used to solve different sub-problems, resulting in greater reliability. Experiments show that the proposed algorithm attains state-of-the-art performance.
在实际应用中，获取的深度图像是不完整的；因此，本文研究深度图像修复。提出了一种以低秩结构和非局部自相似性为特征的新型模型。作为双重约束，低秩结构和非局部自相似性可以充分利用单深度图像的特征来完成修复任务。首先，根据像素值的特征，将图像划分为块，然后形成相似块组和三维排列。然后，应用变量分裂技术将修复问题有效地分解为低秩约束和非局部自相似性约束的子问题。最后，采用不同的策略来解决不同的子问题，从而提高可靠性。实验表明，所提算法达到了当前最优性能。
