Abstract
Depth image-based rendering has gained significant acceptance having been at the frontiers of understanding and realization of three-dimensional and free-view televisions. The appearance of holes on a rendered image and the occurrence of depth discontinuity on the surface of the object at virtual image which forms the basis of view-dependent depth can be significantly minimized if stringent considerations are exercised on region match measures such as sum of absolute differences, Sum of square differences, and normalized cross-correlation used during interest point detection and feature matching. This paper seeks an understanding of the role played by interest points in the generation of depth map which consequently affects the quality of textured depth map of a virtual viewpoint in between two reference still images from existing cameras.
Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
