Optimal depth recovery using image guided TGV with depth confidence for high-quality view synthesis |
| |
Affiliation: | 1. Core Technology Group, Panasonic R&D Center Singapore, Singapore;2. Department of Computer Engineering, King Mongkutś University of Technology Thonburi, Bangkok, Thailand;3. Department of Electronics and Telecommunication Engineering, King Mongkutś University of Technology Thonburi, Bangkok, Thailand;4. Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210048, China;1. College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China;2. College of Management and Information Engineering, Hunan University of Chinese Medicine, Changsha 410082, China;1. State Key Lab of CAD&CG, Zhejiang University, China;2. Software School of Xiamen University, China;1. Faculty of Arts and Science, Kyushu University, 819-0395, Japan;2. Faculty of Information Science and Electrical Engineering, Kyushu University, Japan;1. Information and Communications Research Laboratories, Industrial Technology Research Institute, Hsinchu, Taiwan;2. Institute of Computer Science and Technology, Peking University, Beijing, China;3. Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan;1. College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China;2. Jiangsu Engineering Center of Network Monitoring, Nanjing University of Information Science & Technology, Nanjing 210044, China;1. School of Digital Media, Jiangnan University, Wuxi 214122, China;2. Faculty of Information Technology, Macau University of Science and Technology, Macau |
| |
Abstract: | This paper presents a new depth image recovery method for RGB-D sensors giving a complete, sharp, and accurate object shape from a noisy boundary depth map. The proposed method uses the image guided Total Generalized Variation (TGV) with the depth confidence. A new directional hole filling method of view synthesis is also investigated to produce natural texture in hole regions whereas reducing blurring effect and preventing distortion. Thus, a high-quality image view can be achieved. Experimental results show that the proposed method yields higher quality recovered depth maps and synthesized image views than other previous methods. |
| |
Keywords: | RGB-D sensors Depth confidence Depth recovery Depth Image Based Rendering (DIBR) View synthesis Hole filling |
本文献已被 ScienceDirect 等数据库收录! |
|