We present an image-based algorithm for interactive rendering depth-of-field effects in images with depth maps. While previously published methods for interactive depth-of-field rendering suffer from various rendering artifacts such as color bleeding and sharpened or darkened silhouettes, our algorithm achieves a significantly improved image quality by employing recently proposed GPU-based pyramid methods for image blurring and pixel disocclusion. Due to the same reason, our algorithm offers an interactive rendering performance on modern GPUs and is suitable for real-time rendering for small circles of confusion. We validate the image quality provided by our algorithm by side-by-side comparisons with results obtained by distributed ray tracing.
Abstract. The rendering of lower resolution image data on higher resolution displays has become a very common task, in particular because of the increasing popularity of webcams, camera phones, and low-bandwidth video streaming. Thus, there is a strong demand for real-time, high-quality image magnification. In this work, we suggest to exploit the high performance of programmable graphics processing units (GPUs) for an adaptive image magnification method. To this end, we propose a GPUfriendly algorithm for image up-sampling by edge-directed image interpolation, which avoids ringing artifacts, excessive blurring, and staircasing of oblique edges. At the same time it features gray-scale invariance, is applicable to color images, and allows for real-time processing of full-screen images on today's GPUs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.