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 stateof-the-art depth-guided inpainting schemes.
All Science Journal Classification (ASJC) codes
- Hardware and Architecture
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering
- Artificial Intelligence