Mikhail Erofeev

Mikhail Erofeev

Auto-generated profile, based on publicly available information

Mikhail Erofeev

Lomonosov Moscow State University

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2014
Verified
Conference Paper
Closed access
YGYury Gitman
Yury Gitman
MEMikhail Erofeev
Mikhail Erofeev
Dmitriy VatolinDmitriy Vatolin
Dmitriy Vatolin
BABolshakov Andrey
Bolshakov Andrey
FAFedorov Alexey
Fedorov Alexey
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 the observer's attention. Our comparisons showed the high objective quality of our proposed approach relative to automatic methods and to the results of single-observer eye tracking with no postprocessing. We demonstrated the practical applicability of our proposed concept to the task of saliency-based video compression.

6 March 2014
Verified
Conference Paper
Closed access
PDF file
ABAlexander Bokov
Alexander Bokov
Dmitriy VatolinDmitriy Vatolin
Dmitriy Vatolin
AZAnton Zachesov
Anton Zachesov
ABAlexander Belous
Alexander Belous
MEMikhail Erofeev
Mikhail Erofeev
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 may appear owing to depth-map blurriness at semitransparent edges: after warping, the object boundary becomes sharper in one view and blurrier in the other, yielding binocular rivalry. To detect this problem we estimate the disparity map, extract boundaries with noticeable differences, and analyze edge-sharpness correspondence between views. We pay additional attention to cases involving a complex background and large occlusions. Another problem is detection of scenes that lack depth volume: we present algorithms for detecting at scenes and scenes with at foreground objects. To identify these problems we analyze the features of the RGB image as well as uniform areas in the depth map. Testing of our algorithms involved examining 10 Blu-ray 3D releases with converted S3D content, including Clash of the Titans, The Avengers, and The Chronicles of Narnia: The Voyage of the Dawn Treader. The algorithms we present enable improved automatic quality assessment during the production stage.

1 September 2017
Verified
Conference Paper
Closed access
VLVitaliy Lyudvichenko
Vitaliy Lyudvichenko
MEMikhail Erofeev
Mikhail Erofeev
YGYury Gitman
Yury Gitman
Dmitriy VatolinDmitriy Vatolin
Dmitriy Vatolin
This work aims to apply visual-attention modeling to attention-based video compression. During our comparison we found that eye-tracking data collected even from a single observer outperforms existing automatic models by a significant margin. Therefore, we offer a semiautomatic approach: using computer-vision algorithms and good initial estimation of eye-tracking data from just one observer to produce high-quality saliency maps that are similar to multi-observer eye tracking and that are appropriate for practical applications. We propose a simple algorithm that is based on temporal coherence of the visual-attention distribution and requires eye tracking of just one observer. The results are as good as an average gaze map for two observers. While preparing the saliency-model comparison, we paid special attention to the quality-measurement procedure. We observe that many modern visual-attention models can be improved by applying simple transforms such as brightness adjustment and blending with the center-prior model. The novel quality-evaluation procedure that we propose is invariant to such transforms. To show the practical use of our semiautomatic approach, we developed a saliency-aware modification of the x264 video encoder and performed subjective and objective evaluations. The modified encoder can serve with any attention model and is publicly available.

14 February 2016 in Electronic Imaging
Verified
Journal Article
Closed access
Dmitriy VatolinDmitriy Vatolin
Dmitriy Vatolin
ABAlexander Bokov
Alexander Bokov
MEMikhail Erofeev
Mikhail Erofeev
VNVyacheslav Napadovsky
Vyacheslav Napadovsky
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
Verified
Journal Article
Closed access
IMIvan Molodetskikh
Ivan Molodetskikh
MEMikhail Erofeev
Mikhail Erofeev
AMAndrey Moskalenko
Andrey Moskalenko
Dmitriy VatolinDmitriy Vatolin
Dmitriy Vatolin

1 May 2021 in Programming and Computer Software
Verified
Journal Article
Closed access
PDF file
AMA. Moskalenko
A. Moskalenko
MEM. Erofeev
M. Erofeev
Dmitriy VatolinDmitriy Vatolin
Dmitriy Vatolin
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.