Dmitriy Vatolin

Learn More
In this paper we propose a novel super-resolution algorithm based on motion compensation and edge-directed spatial interpolation succeeded by fusion via pixel classification. Two high-resolution images are constructed, the first by means of motion compensation and the second by means of edge-directed interpolation. The AdaBoost classifier is then used to(More)
Despite recent progress in the field of video matting, neither public data sets nor even a generally accepted method of measuring quality has yet emerged. In this paper we present an online benchmark for video-matting methods. Using chroma keying and a reflection-aware stop-motion capturing procedure, we prepared 12 test sequences. Then, using subjective(More)
Algorithms for video content compression have been developed very fast during last years. But most of them are still lossy. This fact leads to different artifacts appearing in compressed video due to information losses. Objective metric for blocking artifacts detection and a number of methods for blurring estimation are proposed in this article. They can(More)
This research aims to sufficiently increase the quality of visual-attention modeling to enable practical applications. We found that automatic models are significantly worse at predicting attention than even single-observer eye tracking. We propose a semiautomatic approach that requires eye tracking of only one observer and is based on time consistency of(More)
For practical applications there is a requirement of the global motion estimation that could use existing block matching motion data. In this paper authors propose two global motion estimation methods that are based on block matching motion estimation. These methods estimate different global motion models. One of the proposed method advantages consists in(More)
Creating and processing stereoscopic video imposes additional quality requirements related to view synchronization. In this work we propose a set of algorithms for detecting typical stereoscopic-video problems, which appear owing to imprecise setup of capture equipment or incorrect postprocessing. We developed a methodology for analyzing the quality of S3D(More)
Automatic analysis of stereo-video quality plays an important role in the process of capturing, converting and editing video in 3D format. Although several low-level stereo-video quality metrics were proposed, a lot more challenging problems of high-level stereo-video analysis, such as left-right channel swap detection, are still practically unsearched. The(More)
In this paper we present algorithms for automatically detecting issues specific to converted S3D content. When a depth-image-based rendering approach produces a stereoscopic image, the quality of the result depends on both the depth maps and the warping algorithms. The most common problem with converted S3D video is edge-sharpness mismatch. This artifact(More)
In this paper we describe our methods for estimating stereo video quality and its suitability for certain displays and projectors. The first issue we investigate is that not every 3D video can be viewed comfortably on a given 3D display owing to its particular features, especially parallax. The second issue is the correspondence between left and right(More)