scholarly journals Learning Deep CNN Denoiser Priors for Depth Image Inpainting

2019 ◽  
Vol 9 (6) ◽  
pp. 1103 ◽  
Author(s):  
Zun Li ◽  
Jin Wu
Keyword(s):  
Rapid Development ◽  
Image Inpainting ◽  
Optimization Methods ◽  
Depth Image ◽  
Iteration Algorithm ◽  
Split Bregman ◽  
Depth Images ◽  
Split Bregman Iteration ◽  
Objective Metrics ◽  
Deep Cnn

Due to the rapid development of RGB-D sensors, increasing attention is being paid to depth image applications. Depth images play an important role in computer vision research. In this paper, we address the problem of inpainting for single depth images without corresponding color images as a guide. Within the framework of model-based optimization methods for depth image inpainting, the split Bregman iteration algorithm was used to transform depth image inpainting into the corresponding denoising subproblem. Then, we trained a set of efficient convolutional neural network (CNN) denoisers to solve this subproblem. Experimental results demonstrate the effectiveness of the proposed algorithm in comparison with three traditional methods in terms of visual quality and objective metrics.

scholarly journals Double-Constraint Inpainting Model of a Single-Depth Image

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1797
Author(s):  
Wu Jin ◽  
Li Zun ◽  
Liu Yong
Keyword(s):  
Three Dimensional ◽  
Image Inpainting ◽  
Low Rank ◽  
Depth Image ◽  
Self Similarity ◽  
Splitting Technique ◽  
Depth Images ◽  
Block Groups ◽  
Novel Model ◽  
Double Constraint

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.

scholarly journals Split Bregman Iteration Algorithm for Image Deblurring Using Fourth-Order Total Bounded Variation Regularization Model

2013 ◽  
Vol 2013 ◽  
pp. 1-11 ◽  
Author(s):  
Yi Xu ◽  
Ting-Zhu Huang ◽  
Jun Liu ◽  
Xiao-Guang Lv
Keyword(s):  
Bounded Variation ◽  
Fourth Order ◽  
Convergence Property ◽  
Iteration Algorithm ◽  
Bregman Iteration ◽  
Split Bregman ◽  
Split Bregman Iteration ◽  
Proposed Model ◽  
Optimum Solution

We propose a fourth-order total bounded variation regularization model which could reduce undesirable effects effectively. Based on this model, we introduce an improved split Bregman iteration algorithm to obtain the optimum solution. The convergence property of our algorithm is provided. Numerical experiments show the more excellent visual quality of the proposed model compared with the second-order total bounded variation model which is proposed by Liu and Huang (2010).

scholarly journals RobotP: A Benchmark Dataset for 6D Object Pose Estimation

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1299
Author(s):  
Honglin Yuan ◽  
Tim Hoogenkamp ◽  
Remco C. Veltkamp
Keyword(s):  
Pose Estimation ◽  
Ground Truth ◽  
3D Models ◽  
Depth Image ◽  
Great Success ◽  
Estimation Algorithms ◽  
Depth Images ◽  
Object Pose Estimation ◽  
Image Pairs ◽  
Bounding Boxes

Deep learning has achieved great success on robotic vision tasks. However, when compared with other vision-based tasks, it is difficult to collect a representative and sufficiently large training set for six-dimensional (6D) object pose estimation, due to the inherent difficulty of data collection. In this paper, we propose the RobotP dataset consisting of commonly used objects for benchmarking in 6D object pose estimation. To create the dataset, we apply a 3D reconstruction pipeline to produce high-quality depth images, ground truth poses, and 3D models for well-selected objects. Subsequently, based on the generated data, we produce object segmentation masks and two-dimensional (2D) bounding boxes automatically. To further enrich the data, we synthesize a large number of photo-realistic color-and-depth image pairs with ground truth 6D poses. Our dataset is freely distributed to research groups by the Shape Retrieval Challenge benchmark on 6D pose estimation. Based on our benchmark, different learning-based approaches are trained and tested by the unified dataset. The evaluation results indicate that there is considerable room for improvement in 6D object pose estimation, particularly for objects with dark colors, and photo-realistic images are helpful in increasing the performance of pose estimation algorithms.

Sign in / Sign up

Export Citation Format

Share Document