Image Completion with Hybrid Interpolation in Tensor Representation
The issue of image completion has been developed considerably over the last two decades, and many computational strategies have been proposed to fill-in missing regions in an incomplete image. When the incomplete image contains many small-sized irregular missing areas, a good alternative seems to be...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/3/797 |
| _version_ | 1828384625495375872 |
|---|---|
| author | Rafał Zdunek Tomasz Sadowski |
| author_facet | Rafał Zdunek Tomasz Sadowski |
| author_sort | Rafał Zdunek |
| collection | DOAJ |
| description | The issue of image completion has been developed considerably over the last two decades, and many computational strategies have been proposed to fill-in missing regions in an incomplete image. When the incomplete image contains many small-sized irregular missing areas, a good alternative seems to be the matrix or tensor decomposition algorithms that yield low-rank approximations. However, this approach uses heuristic rank adaptation techniques, especially for images with many details. To tackle the obstacles of low-rank completion methods, we propose to model the incomplete images with overlapping blocks of Tucker decomposition representations where the factor matrices are determined by a hybrid version of the Gaussian radial basis function and polynomial interpolation. The experiments, carried out for various image completion and resolution up-scaling problems, demonstrate that our approach considerably outperforms the baseline and state-of-the-art low-rank completion methods. |
| first_indexed | 2024-12-10T05:05:25Z |
| format | Article |
| id | doaj.art-baaedfec70f849eea85686afd29319cc |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-10T05:05:25Z |
| publishDate | 2020-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-baaedfec70f849eea85686afd29319cc2022-12-22T02:01:15ZengMDPI AGApplied Sciences2076-34172020-01-0110379710.3390/app10030797app10030797Image Completion with Hybrid Interpolation in Tensor RepresentationRafał Zdunek0Tomasz Sadowski1Department of Electronics, Wroclaw University of Science and Technology, Wybrzeze Wyspianskiego 27, 50-370 Wroclaw, PolandDepartment of Electronics, Wroclaw University of Science and Technology, Wybrzeze Wyspianskiego 27, 50-370 Wroclaw, PolandThe issue of image completion has been developed considerably over the last two decades, and many computational strategies have been proposed to fill-in missing regions in an incomplete image. When the incomplete image contains many small-sized irregular missing areas, a good alternative seems to be the matrix or tensor decomposition algorithms that yield low-rank approximations. However, this approach uses heuristic rank adaptation techniques, especially for images with many details. To tackle the obstacles of low-rank completion methods, we propose to model the incomplete images with overlapping blocks of Tucker decomposition representations where the factor matrices are determined by a hybrid version of the Gaussian radial basis function and polynomial interpolation. The experiments, carried out for various image completion and resolution up-scaling problems, demonstrate that our approach considerably outperforms the baseline and state-of-the-art low-rank completion methods.https://www.mdpi.com/2076-3417/10/3/797image completiontensor decomposition modelsimage interpolationimage up-scaling |
| spellingShingle | Rafał Zdunek Tomasz Sadowski Image Completion with Hybrid Interpolation in Tensor Representation Applied Sciences image completion tensor decomposition models image interpolation image up-scaling |
| title | Image Completion with Hybrid Interpolation in Tensor Representation |
| title_full | Image Completion with Hybrid Interpolation in Tensor Representation |
| title_fullStr | Image Completion with Hybrid Interpolation in Tensor Representation |
| title_full_unstemmed | Image Completion with Hybrid Interpolation in Tensor Representation |
| title_short | Image Completion with Hybrid Interpolation in Tensor Representation |
| title_sort | image completion with hybrid interpolation in tensor representation |
| topic | image completion tensor decomposition models image interpolation image up-scaling |
| url | https://www.mdpi.com/2076-3417/10/3/797 |
| work_keys_str_mv | AT rafałzdunek imagecompletionwithhybridinterpolationintensorrepresentation AT tomaszsadowski imagecompletionwithhybridinterpolationintensorrepresentation |