8 papers
SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation
Ivan Molodetskikh, Kirill Malyshev, Mark Mirgaleev +3
Modern image super-resolution methods generate detailed, visually appealing results, but they often introduce visual artifacts: unnatural patterns and texture distortions that degr…
Exploring Real-Time Super-Resolution: Benchmarking and Fine-Tuning for Streaming Content
Evgeney Bogatyrev, Khaled Abud, Ivan Molodetskikh +2
Recent advancements in real-time super-resolution have enabled higher-quality video streaming, yet existing methods struggle with the unique challenges of compressed video content.…
Prominence-Aware Artifact Detection and Dataset for Image Super-Resolution
Ivan Molodetskikh, Kirill Malyshev, Mark Mirgaleev +3
Generative single-image super-resolution (SISR) is advancing rapidly, yet even state-of-the-art models produce visual artifacts: unnatural patterns and texture distortions that deg…
SR+Codec: a Benchmark of Super-Resolution for Video Compression Bitrate Reduction
Evgeney Bogatyrev, Ivan Molodetskikh, Dmitriy Vatolin
In recent years, there has been significant interest in Super-Resolution (SR), which focuses on generating a high-resolution image from a low-resolution input. Deep learning-based…
JPEG AI Image Compression Visual Artifacts: Detection Methods and Dataset
Daria Tsereh, Mark Mirgaleev, Ivan Molodetskikh +2
Learning-based image compression methods have improved in recent years and started to outperform traditional codecs. However, neural-network approaches can unexpectedly introduce v…
Machine vision-aware quality metrics for compressed image and video assessment
Mikhail Dremin, Konstantin Kozhemyakov, Ivan Molodetskikh +3
A main goal in developing video-compression algorithms is to enhance human-perceived visual quality while maintaining file size. But modern video-analysis efforts such as detection…