High‐order Markov random field for single depth image super‐resolution
Although there is an increasing interest in employing the depth data in computer vision applications, the spatial resolution of depth maps is still limited compared with typical visible‐light images. A novel method is proposed to synthetically improve the spatial resolution of a single depth image....
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2017-12-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2016.0373 |
| _version_ | 1797684380025487360 |
|---|---|
| author | Elham Shabaninia Ahmad Reza Naghsh‐Nilchi Shohreh Kasaei |
| author_facet | Elham Shabaninia Ahmad Reza Naghsh‐Nilchi Shohreh Kasaei |
| author_sort | Elham Shabaninia |
| collection | DOAJ |
| description | Although there is an increasing interest in employing the depth data in computer vision applications, the spatial resolution of depth maps is still limited compared with typical visible‐light images. A novel method is proposed to synthetically improve the spatial resolution of a single depth image. It integrates the higher‐order terms into the Markov random field (MRF) formulation of example‐based methods in order to improve the representational power of those methods. The inference is performed by approximately minimising the higher‐order multi‐label MRF energies. In addition, to improve the efficiency of the inference algorithm, a hierarchical scheme on the number of MRF states is proposed. First, a large number of states are used to obtain an initial labelling by solving the minimisation problem of inference for only the first‐order energies. Then, the problem is solved for the higher‐order energies in a smaller number of states. Performance comparisons show that proposed method improves the results of first‐order approaches that are based on simple four‐connected MRF graph structure, both qualitatively and quantitatively. |
| first_indexed | 2024-03-12T00:28:53Z |
| format | Article |
| id | doaj.art-18341f0bdef04cfea32d5e1f4020bcd9 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:28:53Z |
| publishDate | 2017-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-18341f0bdef04cfea32d5e1f4020bcd92023-09-15T10:25:59ZengWileyIET Computer Vision1751-96321751-96402017-12-0111868369010.1049/iet-cvi.2016.0373High‐order Markov random field for single depth image super‐resolutionElham Shabaninia0Ahmad Reza Naghsh‐Nilchi1Shohreh Kasaei2Department of Artificial Intelligence, Faculty of Computer EngineeringUniversity of IsfahanIsfahanIranDepartment of Artificial Intelligence, Faculty of Computer EngineeringUniversity of IsfahanIsfahanIranDepartment of Computer EngineeringSharif University of TechnologyTehranIranAlthough there is an increasing interest in employing the depth data in computer vision applications, the spatial resolution of depth maps is still limited compared with typical visible‐light images. A novel method is proposed to synthetically improve the spatial resolution of a single depth image. It integrates the higher‐order terms into the Markov random field (MRF) formulation of example‐based methods in order to improve the representational power of those methods. The inference is performed by approximately minimising the higher‐order multi‐label MRF energies. In addition, to improve the efficiency of the inference algorithm, a hierarchical scheme on the number of MRF states is proposed. First, a large number of states are used to obtain an initial labelling by solving the minimisation problem of inference for only the first‐order energies. Then, the problem is solved for the higher‐order energies in a smaller number of states. Performance comparisons show that proposed method improves the results of first‐order approaches that are based on simple four‐connected MRF graph structure, both qualitatively and quantitatively.https://doi.org/10.1049/iet-cvi.2016.0373high-order Markov random fieldsingle depth image superresolutiondepth datacomputer vision applicationsspatial resolution improvementdepth maps |
| spellingShingle | Elham Shabaninia Ahmad Reza Naghsh‐Nilchi Shohreh Kasaei High‐order Markov random field for single depth image super‐resolution IET Computer Vision high-order Markov random field single depth image superresolution depth data computer vision applications spatial resolution improvement depth maps |
| title | High‐order Markov random field for single depth image super‐resolution |
| title_full | High‐order Markov random field for single depth image super‐resolution |
| title_fullStr | High‐order Markov random field for single depth image super‐resolution |
| title_full_unstemmed | High‐order Markov random field for single depth image super‐resolution |
| title_short | High‐order Markov random field for single depth image super‐resolution |
| title_sort | high order markov random field for single depth image super resolution |
| topic | high-order Markov random field single depth image superresolution depth data computer vision applications spatial resolution improvement depth maps |
| url | https://doi.org/10.1049/iet-cvi.2016.0373 |
| work_keys_str_mv | AT elhamshabaninia highordermarkovrandomfieldforsingledepthimagesuperresolution AT ahmadrezanaghshnilchi highordermarkovrandomfieldforsingledepthimagesuperresolution AT shohrehkasaei highordermarkovrandomfieldforsingledepthimagesuperresolution |