Abstract
Multi‐view image plays an important role in many kinds of 3D display techniques. However, the acquisition of multi‐view image is usually high‐cost and complicated. Inspired by the research of Deep3D, we constructed view synthesis model and proposed a low‐cost multi‐view image synthesis method which can convert 2D image into multi‐view image automatically. To evaluate the performance of proposed method, we compared the synthesized multi‐view image with ground truth and carried out subjective experiments with autostereoscopic display devices. The result suggests that our methods have great potential on multi‐view image synthesis.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
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
