Depth image based rendering (DIBR), which is utilized to render virtual views with a color image and the corresponding depth map, is one of the key procedures in the 2D to 3D conversion process. However, some troubling problems, such as depth edge misalignment, disocclusion occurrences and cracks at resampling, still exist in current DIBR systems. To solve these problems, in this paper, we present a robust depth image based rendering scheme for stereoscopic view synthesis. The cores of the proposed scheme are two depth map filters which share a common domain transform based filtering framework. As a first step, a filter of this framework is carried out to realize texture-depth boundary alignments and directional disocclusion reduction smoothing simultaneously. Then after depth map 3D warping, another adaptive filter is used on the warped depth maps with delivered scene gradient structures to further diminish the remaining cracks and noises. Finally, with the optimized depth map of the virtual view, backward texture warping is adopted to retrieve the final texture virtual view. The proposed scheme enables to yield visually satisfactory results for high quality 2D to 3D conversion. Experimental results demonstrate the excellent performances of the proposed approach.
Wei LIU
Nanyang Normal University
Yun Qi TANG
People's Public Security University of China
Jian Wei DING
People's Public Security University of China
Ming Yue CUI
Nanyang Normal University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Wei LIU, Yun Qi TANG, Jian Wei DING, Ming Yue CUI, "A Robust Depth Image Based Rendering Scheme for Stereoscopic View Synthesis with Adaptive Domain Transform Based Filtering Framework" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 12, pp. 3138-3149, December 2018, doi: 10.1587/transinf.2018EDP7069.
Abstract: Depth image based rendering (DIBR), which is utilized to render virtual views with a color image and the corresponding depth map, is one of the key procedures in the 2D to 3D conversion process. However, some troubling problems, such as depth edge misalignment, disocclusion occurrences and cracks at resampling, still exist in current DIBR systems. To solve these problems, in this paper, we present a robust depth image based rendering scheme for stereoscopic view synthesis. The cores of the proposed scheme are two depth map filters which share a common domain transform based filtering framework. As a first step, a filter of this framework is carried out to realize texture-depth boundary alignments and directional disocclusion reduction smoothing simultaneously. Then after depth map 3D warping, another adaptive filter is used on the warped depth maps with delivered scene gradient structures to further diminish the remaining cracks and noises. Finally, with the optimized depth map of the virtual view, backward texture warping is adopted to retrieve the final texture virtual view. The proposed scheme enables to yield visually satisfactory results for high quality 2D to 3D conversion. Experimental results demonstrate the excellent performances of the proposed approach.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDP7069/_p
Copy
@ARTICLE{e101-d_12_3138,
author={Wei LIU, Yun Qi TANG, Jian Wei DING, Ming Yue CUI, },
journal={IEICE TRANSACTIONS on Information},
title={A Robust Depth Image Based Rendering Scheme for Stereoscopic View Synthesis with Adaptive Domain Transform Based Filtering Framework},
year={2018},
volume={E101-D},
number={12},
pages={3138-3149},
abstract={Depth image based rendering (DIBR), which is utilized to render virtual views with a color image and the corresponding depth map, is one of the key procedures in the 2D to 3D conversion process. However, some troubling problems, such as depth edge misalignment, disocclusion occurrences and cracks at resampling, still exist in current DIBR systems. To solve these problems, in this paper, we present a robust depth image based rendering scheme for stereoscopic view synthesis. The cores of the proposed scheme are two depth map filters which share a common domain transform based filtering framework. As a first step, a filter of this framework is carried out to realize texture-depth boundary alignments and directional disocclusion reduction smoothing simultaneously. Then after depth map 3D warping, another adaptive filter is used on the warped depth maps with delivered scene gradient structures to further diminish the remaining cracks and noises. Finally, with the optimized depth map of the virtual view, backward texture warping is adopted to retrieve the final texture virtual view. The proposed scheme enables to yield visually satisfactory results for high quality 2D to 3D conversion. Experimental results demonstrate the excellent performances of the proposed approach.},
keywords={},
doi={10.1587/transinf.2018EDP7069},
ISSN={1745-1361},
month={December},}
Copy
TY - JOUR
TI - A Robust Depth Image Based Rendering Scheme for Stereoscopic View Synthesis with Adaptive Domain Transform Based Filtering Framework
T2 - IEICE TRANSACTIONS on Information
SP - 3138
EP - 3149
AU - Wei LIU
AU - Yun Qi TANG
AU - Jian Wei DING
AU - Ming Yue CUI
PY - 2018
DO - 10.1587/transinf.2018EDP7069
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2018
AB - Depth image based rendering (DIBR), which is utilized to render virtual views with a color image and the corresponding depth map, is one of the key procedures in the 2D to 3D conversion process. However, some troubling problems, such as depth edge misalignment, disocclusion occurrences and cracks at resampling, still exist in current DIBR systems. To solve these problems, in this paper, we present a robust depth image based rendering scheme for stereoscopic view synthesis. The cores of the proposed scheme are two depth map filters which share a common domain transform based filtering framework. As a first step, a filter of this framework is carried out to realize texture-depth boundary alignments and directional disocclusion reduction smoothing simultaneously. Then after depth map 3D warping, another adaptive filter is used on the warped depth maps with delivered scene gradient structures to further diminish the remaining cracks and noises. Finally, with the optimized depth map of the virtual view, backward texture warping is adopted to retrieve the final texture virtual view. The proposed scheme enables to yield visually satisfactory results for high quality 2D to 3D conversion. Experimental results demonstrate the excellent performances of the proposed approach.
ER -