A novel holes filling method based on layered depth map and patch sparsity for complex-scene images. (August 2021)

• Record Type: Journal Article
• Authors: Bi, Xiaodong; Yang, Bailin; Zeng, Jia; Wei, Tianxiang; Xiang, Yiming
• Is Part Of: Microelectronics journal. Volume 114(2021)
• Publication Date: 2021-08
• Subjects: Complex scene -- Hole filling -- Layered depth map -- Patch sparsity -- Exemplar matching; Microelectronics -- Periodicals; Microélectronique -- Périodiques; Microelectronics; Electronic journals; Journals - contents and abstracts; Periodicals; 621.3805
• DOI: 10.1016/j.mejo.2021.105140
• Languages: English
• ISSNs: 0959-8324

Abstract

Abstract: The depth image based rendering (DIBR) is a key technology in the emerging 3D video and 3D-TV, which uses a single texture image and the corresponding depth map to generate the virtual views. A critical problem occurs when the virtual view generation refers to regions covered by foreground objects in the original view, which might be disoccluded in the synthetized view. In this paper, a holes filling method based on layered depth map and patch sparsity for complex scenes is proposed. The proposed approach consists of three parts. The first part refers to use of the depth information to divide the complex scene into simple scenes, which represents the separation of foreground and background with a special depth value using an adaptable layered method based on the depth map. The second part represents the holes filling in the depth map using the patch sparsity. Finally, in the third part, the background information and the filled depth map are used to fill the holes in the color map. The experimental results have indicated that compared to other methods, the proposed method provides better quality of synthetized complex scene and 3D scene.