14 February 2016 in Electronic Imaging
In this paper we present a large-scale analysis of S3D-movie technical quality spanning a large portion of stereoscopic-cinema history. We evaluated 105 Blu-ray 3D releases, including titles like the 1954 classic Dial M for Murder, as well as contemporary stereoscopic productions like Life of Pi and The Great Gatsby. The analysis is based on objective quality metrics designed to detect specific types of artifacts, including swapped channels, inconsistencies between the stereoscopic views (color, sharpness and geometric as well as temporal asynchrony) and many others. The main challenges we had to overcome were the enormous amount of computational resources and disk space that such analyses require as well as algorithmic difficulties in developing some of the more advanced objective quality metrics. Our study clarifies the quality trends and problems of S3D movie production in general and provides a better understanding of how effectively quality control has been applied to particular movies compared with the overall trend.
15 March 2022 in Digital Signal Processing
1 May 2021 in Programming and Computer Software
In recent years, the field of image inpainting has developed rapidly, learning based approaches show impressive results in the task of filling missing parts in an image. But most deep methods are strongly tied to the resolution of the images on which they were trained. A slight resolution increase leads to serious artifacts and unsatisfactory filling quality. These methods are therefore unsuitable for interactive image processing. In this article, we propose a method that solves the problem of inpainting arbitrary-size images. We also describe a way to better restore texture fragments in the filled area. For this, we propose to use information from neighboring pixels by shifting the original image in four directions. Moreover, this approach can work with existing inpainting models, making them almost resolution independent without the need for retraining.