A Generalized Depth Estimation Algorithm with a Single Image
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
International Journal of Computer Vision
View synthesis using stereo vision
View synthesis using stereo vision
Generating the depth map from the motion information of H.264-encoded 2D video sequence
Journal on Image and Video Processing - Special issue on selected papers from multimedia modeling conference 2009
Hi-index | 0.00 |
An efficient method that estimates the depth map of a 3D scene using the motion information of its H.264-encoded 2D video is presented. Our proposed method employs a revised version of the motion information. This is obtained based on the characteristics of the 3D human visual perception. The low complexity of our approach and its compatibility with future broadcasting networks allow its real-time implementation at the receiver, i.e. the 3D signal is delivered at no additional burden to the network. Performance evaluations show that our approach outperforms the other existing H.264-based technique by up to 1.5 dB PSNR i.e. it provides more realistic depth information of the scene. Moreover the subjective comparison of results (obtained by viewers watching the generated stereo video sequences on 3D display system) confirms the higher efficiency of our method.