Abstract

Depth estimation is one of the key technologies of FTV system. To increase depth accuracy, a depth estimation method which can preserve temporal consistency is proposed. For current view, depth values of the previous frame and motion information between current and its previous frame are used as constraint conditions to estimate depth map of current frame, thus preserve temporal consistency of depth maps in the two successive frames. Experiment results show that not only accuracy of depth edges in depth maps is increased, but also temporal consistency of depth maps is preserved well.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call