Deep Convolutional Grid Warping Network for Joint Depth Map Upsampling
Depth maps play an important role in the representation of 3D information. They are often simultaneously acquired with color images; however, their resolution is significantly lower than that of color images owing to hardware limitations. In this paper, we propose a novel approach to upsample depth...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9163094/ |
| _version_ | 1818875466713399296 |
|---|---|
| author | Yoonmo Yang Dongsin Kim Byung Tae Oh |
| author_facet | Yoonmo Yang Dongsin Kim Byung Tae Oh |
| author_sort | Yoonmo Yang |
| collection | DOAJ |
| description | Depth maps play an important role in the representation of 3D information. They are often simultaneously acquired with color images; however, their resolution is significantly lower than that of color images owing to hardware limitations. In this paper, we propose a novel approach to upsample depth maps by using geometric deformation instead of pixel value refinement, which is employed in a majority of existing methods. This approach, known as grid warping, displaces the position of blurred pixels around the edge towards the center of the edge. The displacement vector for warping is obtained from an analysis of the corresponding high-resolution color image. Furthermore, we propose an edge signal and displacement vector modeling for a more effective analysis. The experimental results show that the proposed method significantly improves the quantitative and visual performance, as compared to state-of-the-art methods. The source codes of the proposed method will be available at https://github.com/yym064/DeepGridWarp. |
| first_indexed | 2024-12-19T13:26:57Z |
| format | Article |
| id | doaj.art-60128432b94442538470b722c42ed044 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T13:26:57Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-60128432b94442538470b722c42ed0442022-12-21T20:19:32ZengIEEEIEEE Access2169-35362020-01-01814758014759010.1109/ACCESS.2020.30152099163094Deep Convolutional Grid Warping Network for Joint Depth Map UpsamplingYoonmo Yang0https://orcid.org/0000-0003-2816-1685Dongsin Kim1Byung Tae Oh2https://orcid.org/0000-0003-1437-2422School of Electronics and Information Engineering, Korea Aerospace University, Goyang, South KoreaSchool of Electronics and Information Engineering, Korea Aerospace University, Goyang, South KoreaSchool of Electronics and Information Engineering, Korea Aerospace University, Goyang, South KoreaDepth maps play an important role in the representation of 3D information. They are often simultaneously acquired with color images; however, their resolution is significantly lower than that of color images owing to hardware limitations. In this paper, we propose a novel approach to upsample depth maps by using geometric deformation instead of pixel value refinement, which is employed in a majority of existing methods. This approach, known as grid warping, displaces the position of blurred pixels around the edge towards the center of the edge. The displacement vector for warping is obtained from an analysis of the corresponding high-resolution color image. Furthermore, we propose an edge signal and displacement vector modeling for a more effective analysis. The experimental results show that the proposed method significantly improves the quantitative and visual performance, as compared to state-of-the-art methods. The source codes of the proposed method will be available at https://github.com/yym064/DeepGridWarp.https://ieeexplore.ieee.org/document/9163094/Depth map upsamplingjoint upsamplinggrid warpingdeep learningCNN |
| spellingShingle | Yoonmo Yang Dongsin Kim Byung Tae Oh Deep Convolutional Grid Warping Network for Joint Depth Map Upsampling IEEE Access Depth map upsampling joint upsampling grid warping deep learning CNN |
| title | Deep Convolutional Grid Warping Network for Joint Depth Map Upsampling |
| title_full | Deep Convolutional Grid Warping Network for Joint Depth Map Upsampling |
| title_fullStr | Deep Convolutional Grid Warping Network for Joint Depth Map Upsampling |
| title_full_unstemmed | Deep Convolutional Grid Warping Network for Joint Depth Map Upsampling |
| title_short | Deep Convolutional Grid Warping Network for Joint Depth Map Upsampling |
| title_sort | deep convolutional grid warping network for joint depth map upsampling |
| topic | Depth map upsampling joint upsampling grid warping deep learning CNN |
| url | https://ieeexplore.ieee.org/document/9163094/ |
| work_keys_str_mv | AT yoonmoyang deepconvolutionalgridwarpingnetworkforjointdepthmapupsampling AT dongsinkim deepconvolutionalgridwarpingnetworkforjointdepthmapupsampling AT byungtaeoh deepconvolutionalgridwarpingnetworkforjointdepthmapupsampling |