18 January 2010 Maximizing inpainting efficiency without sacrificing quality
Author Affiliations +
We propose a quality-aware computational optimization of inpainting based upon the intelligent application of a battery of inpainting methods. By leveraging the Decision-Action-Reward Network (DARN) formalism and a bottom-up model of human visual attention, methods are selected for optimal local use via an adjustable quality-time tradeoff and (empirical) training statistics aimed at minimizing observer foveal attention to inpainted regions. Results are shown for object removal in high-resolution consumer video, including a comparison of output quality and efficiency with homogeneous inpainting applications.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Paul A. Ardis, Christopher M. Brown, "Maximizing inpainting efficiency without sacrificing quality", Proc. SPIE 7529, Image Quality and System Performance VII, 75290U (18 January 2010); doi: 10.1117/12.837772; https://doi.org/10.1117/12.837772

Back to Top