Learning Deep CNN Denoiser Priors for Depth Image Inpainting
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. W...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2076-3417/9/6/1103 |
| _version_ | 1818110675735543808 |
|---|---|
| author | Zun Li Jin Wu |
| author_facet | Zun Li Jin Wu |
| author_sort | Zun Li |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-11T02:50:55Z |
| format | Article |
| id | doaj.art-1b4e3c3d92cd46158577324c07920859 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-11T02:50:55Z |
| publishDate | 2019-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1b4e3c3d92cd46158577324c079208592022-12-22T01:23:17ZengMDPI AGApplied Sciences2076-34172019-03-0196110310.3390/app9061103app9061103Learning Deep CNN Denoiser Priors for Depth Image InpaintingZun Li0Jin Wu1School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, Hubei, ChinaSchool of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, Hubei, ChinaDue 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.http://www.mdpi.com/2076-3417/9/6/1103depth image inpaintingmodel-based optimization methodssplit Bregman iteration algorithmconvolutional neural network (CNN) denoiser |
| spellingShingle | Zun Li Jin Wu Learning Deep CNN Denoiser Priors for Depth Image Inpainting Applied Sciences depth image inpainting model-based optimization methods split Bregman iteration algorithm convolutional neural network (CNN) denoiser |
| title | Learning Deep CNN Denoiser Priors for Depth Image Inpainting |
| title_full | Learning Deep CNN Denoiser Priors for Depth Image Inpainting |
| title_fullStr | Learning Deep CNN Denoiser Priors for Depth Image Inpainting |
| title_full_unstemmed | Learning Deep CNN Denoiser Priors for Depth Image Inpainting |
| title_short | Learning Deep CNN Denoiser Priors for Depth Image Inpainting |
| title_sort | learning deep cnn denoiser priors for depth image inpainting |
| topic | depth image inpainting model-based optimization methods split Bregman iteration algorithm convolutional neural network (CNN) denoiser |
| url | http://www.mdpi.com/2076-3417/9/6/1103 |
| work_keys_str_mv | AT zunli learningdeepcnndenoiserpriorsfordepthimageinpainting AT jinwu learningdeepcnndenoiserpriorsfordepthimageinpainting |