Spatially Adaptive Tensor Total Variation-Tikhonov Model for Depth Image Super Resolution
Depth images play an important role in 3-D applications. However, due to the limitation of depth acquisition equipment, the acquired depth images are usually in limited resolution. In this paper, a spatially adaptive tensor total variation-Tikhonov model is proposed to solve this problem. The tensor...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2017-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/7953754/ |
| _version_ | 1830357386385162240 |
|---|---|
| author | Gang Zhong Sen Xiang Peng Zhou Li Yu |
| author_facet | Gang Zhong Sen Xiang Peng Zhou Li Yu |
| author_sort | Gang Zhong |
| collection | DOAJ |
| description | Depth images play an important role in 3-D applications. However, due to the limitation of depth acquisition equipment, the acquired depth images are usually in limited resolution. In this paper, a spatially adaptive tensor total variation-Tikhonov model is proposed to solve this problem. The tensor total variation regularization is adopted to maintain sharp edges that reflect latent discontinuities in the real world, while the Tikhonov regularization ensures that depth changes smoothly inside objects. Furthermore, a fused edge map is proposed to indicate edge regions and balance both regularization terms. In edge regions, tensor total variation regularization is predominant, thus edge blurring artifacts are suppressed. In non-edge regions, Tikhonov regularization plays a more important role to suppress staircasing artifacts. Specifically, texture edges are removed in the fused edge map, and texture copying artifacts are avoided. Experimental results demonstrate the effectiveness and superiority of the proposed framework. Moreover, the proposed method yields much sharper edges and a lower percentage of bad pixels. |
| first_indexed | 2024-12-20T02:22:44Z |
| format | Article |
| id | doaj.art-e21f64dbf39c46ac8f1efc8d5d8dc3fa |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T02:22:44Z |
| publishDate | 2017-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e21f64dbf39c46ac8f1efc8d5d8dc3fa2022-12-21T19:56:47ZengIEEEIEEE Access2169-35362017-01-015138571386710.1109/ACCESS.2017.27159817953754Spatially Adaptive Tensor Total Variation-Tikhonov Model for Depth Image Super ResolutionGang Zhong0https://orcid.org/0000-0001-6734-4121Sen Xiang1Peng Zhou2Li Yu3Huazhong University of Science and Technology, Wuhan, ChinaSchool of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan, ChinaHuazhong University of Science and Technology, Wuhan, ChinaHuazhong University of Science and Technology, Wuhan, ChinaDepth images play an important role in 3-D applications. However, due to the limitation of depth acquisition equipment, the acquired depth images are usually in limited resolution. In this paper, a spatially adaptive tensor total variation-Tikhonov model is proposed to solve this problem. The tensor total variation regularization is adopted to maintain sharp edges that reflect latent discontinuities in the real world, while the Tikhonov regularization ensures that depth changes smoothly inside objects. Furthermore, a fused edge map is proposed to indicate edge regions and balance both regularization terms. In edge regions, tensor total variation regularization is predominant, thus edge blurring artifacts are suppressed. In non-edge regions, Tikhonov regularization plays a more important role to suppress staircasing artifacts. Specifically, texture edges are removed in the fused edge map, and texture copying artifacts are avoided. Experimental results demonstrate the effectiveness and superiority of the proposed framework. Moreover, the proposed method yields much sharper edges and a lower percentage of bad pixels.https://ieeexplore.ieee.org/document/7953754/Depth image super resolutiontensor total variation regularizationTikhonov regularization |
| spellingShingle | Gang Zhong Sen Xiang Peng Zhou Li Yu Spatially Adaptive Tensor Total Variation-Tikhonov Model for Depth Image Super Resolution IEEE Access Depth image super resolution tensor total variation regularization Tikhonov regularization |
| title | Spatially Adaptive Tensor Total Variation-Tikhonov Model for Depth Image Super Resolution |
| title_full | Spatially Adaptive Tensor Total Variation-Tikhonov Model for Depth Image Super Resolution |
| title_fullStr | Spatially Adaptive Tensor Total Variation-Tikhonov Model for Depth Image Super Resolution |
| title_full_unstemmed | Spatially Adaptive Tensor Total Variation-Tikhonov Model for Depth Image Super Resolution |
| title_short | Spatially Adaptive Tensor Total Variation-Tikhonov Model for Depth Image Super Resolution |
| title_sort | spatially adaptive tensor total variation tikhonov model for depth image super resolution |
| topic | Depth image super resolution tensor total variation regularization Tikhonov regularization |
| url | https://ieeexplore.ieee.org/document/7953754/ |
| work_keys_str_mv | AT gangzhong spatiallyadaptivetensortotalvariationtikhonovmodelfordepthimagesuperresolution AT senxiang spatiallyadaptivetensortotalvariationtikhonovmodelfordepthimagesuperresolution AT pengzhou spatiallyadaptivetensortotalvariationtikhonovmodelfordepthimagesuperresolution AT liyu spatiallyadaptivetensortotalvariationtikhonovmodelfordepthimagesuperresolution |