A Depth-Guided Inpainting Scheme Based on Foreground Depth-Layer Removal for High Quality 2D to 3D Video Conversion

• Published in: IEICE Transactions on Information and Systems Vol. E96.D; no. 11; pp. 2483 - 2486
• Main Authors: CHOI, Jangwon, CHOE, Yoonsik, KIM, Yong-Goo
• Format: Journal Article
• Language: English; Japanese
• Published: Oxford The Institute of Electronics, Information and Communication Engineers 2013; Oxford University Press
• Subjects: 2D to 3D conversion; Applied sciences; Conversion; depth image-based rendering; depth-guided inpainting; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; foreground depth layer; hole filling; Image detection; Image processing; Information, signal and communications theory; Signal and communications theory; Signal processing; Signal, noise; State of the art; Telecommunications and information theory; Three dimensional; Two dimensional; depth image-based rendering; State of the art; Background; Image rendering; foreground depth layer; Video signal processing; 2D to 3D conversion; Image quality; Foreground; Tridimensional image; Signal conversion; hole filling; depth-guided inpainting
• ISSN: 0916-8532; 1745-1361
• DOI: 10.1587/transinf.E96.D.2483

This letter proposes a novel depth-guided inpainting scheme for the high quality hole-filling in 2D-to-3D video conversion. The proposed scheme detects and removes foreground depth layers in an image patch, enabling appropriate patch formation using only disoccluded background information. This background only patch formation helps to avoid the propagation of wrong depths over hole area, and thus improve the overall quality of converted 3D video experience. Experimental results demonstrate the proposed scheme provides visually much more pleasing inpainting results with better preserved object edges compared to the state-of-the-art depth-guided inpainting schemes.