Abstract
The main problems with virtual view synthesis based on the common Depth-Image-Based Rendering (DIBR) algorithms are image rectification, depth map and image de-rectification that lead to additional computational load and image distortion. In this paper an efficient and reliable method based on the concept of Correspondence Field and minimum distance among spatial positions of corresponding pixels is proposed to synthesize virtual view images without image rectification, depth map and image de-rectification steps. Simulated multi-view images are used to evaluate the proposed algorithm. By comparison with DIBR algorithms, simulation results show that on average, PSNR is 4.37 dB (14.8%) higher, SSIM is 0.057 (6.2%) more, UNIQUE is 0.13 (20%) more, the running time is 47.34 s (24.5%) less and wrong pixels are 4.35 (38.5%) less.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.