Ivan Molodetskikh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Ivan Molodetskikh has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Dmitriy Vatolin
Lomonosov Moscow State University, Moscow, Russia
9 shared publications - Artem Borisov
Lomonosov Moscow State University, Moscow, Russia
3 shared publications - Evgeney Bogatyrev
MSU Institute for Artificial Intelligence, Moscow, Russian Federation
2 shared publications Haibo Lei
Tencent
2 shared publications- Jianzhao Liu
Bytedance
2 shared publications Jingwen Xu
Bytedance
2 shared publications
Latest Publications
- Open Access
- 31 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 60229-60251
VSRQAD: Video Super-Resolution Quality Assessment Dataset and Benchmark
Image and video quality assessment is crucial for modern video processing. While extensive research has been devoted to benchmarking quality assessment methods on native-resolution content, systematic evaluations for super-resolved video remain largely unexplored. In this paper, we introduce the Video Super-Resolution Quality Assessment Dataset (VSRQAD), comparing 50 image and video quality metrics on videos upscaled 2× and 4× using 11 single- and multi-frame super-resolution algorithms. The benchmark includes over 2,000 super-resolved videos and 180,000 pairwise subjective judgments, enabling large-scale analysis of how metrics capture perceptual quality. Results reveal differences in metric reliability across scaling factors and algorithms, highlighting scenarios where current metrics succeed or fail. By releasing the benchmark and human judgment dataset, we support research on perceptually driven evaluation and quality assessment for AI-enhanced video content. The benchmark and dataset are available at https://videoprocessing.ai/benchmarks/super-resolution-metrics.html.
- 31 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 60229-60251
Open AccessVSRQAD: Video Super-Resolution Quality Assessment Dataset and Benchmark
Image and video quality assessment is crucial for modern video processing. While extensive research has been devoted to benchmarking quality assessment methods on native-resolution content, systematic evaluations for super-resolved video remain largely unexplored. In this paper, we introduce the Video Super-Resolution Quality Assessment Dataset (VSRQAD), comparing 50 image and video quality metrics on videos upscaled 2× and 4× using 11 single- and multi-frame super-resolution algorithms. The benchmark includes over 2,000 super-resolved videos and 180,000 pairwise subjective judgments, enabling large-scale analysis of how metrics capture perceptual quality. Results reveal differences in metric reliability across scaling factors and algorithms, highlighting scenarios where current metrics succeed or fail. By releasing the benchmark and human judgment dataset, we support research on perceptually driven evaluation and quality assessment for AI-enhanced video content. The benchmark and dataset are available at https://videoprocessing.ai/benchmarks/super-resolution-metrics.html.
- 12 May 2025
- Published by Springer Nature
- p. 160-177
AIM 2024 Challenge on Video Super-Resolution Quality Assessment: Methods and Results
- 12 May 2025
- Published by Springer Nature
- p. 160-177
AIM 2024 Challenge on Video Super-Resolution Quality Assessment: Methods and Results
- 2 December 2024
- Published by Springer Nature
- p. 266-282
Machine Vision-Aware Quality Metrics for Compressed Image and Video Assessment
- 2 December 2024
- Published by Springer Nature
- p. 266-282
Machine Vision-Aware Quality Metrics for Compressed Image and Video Assessment
- Open Access
JPEG AI Image Compression Visual Artifacts: Detection Methods and Dataset
Learning-based image compression methods have improved in recent years and started to outperform traditional codecs. However, neural-network approaches can unexpectedly introduce visual artifacts in some images. We therefore propose methods to separately detect three types of artifacts (texture and boundary degradation, color change, and text corruption), to localize the affected regions, and to quantify the artifact strength. We consider only those regions that exhibit distortion due solely to the neural compression but that a traditional codec recovers successfully at a comparable bitrate. We employed our methods to collect artifacts for the JPEG AI verification model with respect to HM-18.0, the H.265 reference software. We processed about 350,000 unique images from the Open Images dataset using different compression-quality parameters; the result is a dataset of 46,440 artifacts validated through crowd-sourced subjective assessment. Our proposed dataset and methods are valuable for testing neural-network-based image codecs, identifying bugs in these codecs, and enhancing their performance. We make source code of the methods and the dataset publicly available.
Open AccessJPEG AI Image Compression Visual Artifacts: Detection Methods and Dataset
Learning-based image compression methods have improved in recent years and started to outperform traditional codecs. However, neural-network approaches can unexpectedly introduce visual artifacts in some images. We therefore propose methods to separately detect three types of artifacts (texture and boundary degradation, color change, and text corruption), to localize the affected regions, and to quantify the artifact strength. We consider only those regions that exhibit distortion due solely to the neural compression but that a traditional codec recovers successfully at a comparable bitrate. We employed our methods to collect artifacts for the JPEG AI verification model with respect to HM-18.0, the H.265 reference software. We processed about 350,000 unique images from the Open Images dataset using different compression-quality parameters; the result is a dataset of 46,440 artifacts validated through crowd-sourced subjective assessment. Our proposed dataset and methods are valuable for testing neural-network-based image codecs, identifying bugs in these codecs, and enhancing their performance. We make source code of the methods and the dataset publicly available.
- Open Access
Machine vision-aware quality metrics for compressed image and video assessment
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 and recognition, which are integral to video surveillance and autonomous vehicles, involve so much data that they necessitate machine-vision processing with minimal human intervention. In such cases, the video codec must be optimized for machine vision. This paper explores the effects of compression on detection and recognition algorithms (objects, faces, and license plates) and introduces novel full-reference image/video-quality metrics for each task, tailored to machine vision. Experimental results indicate our proposed metrics correlate better with the machine-vision results for the respective tasks than do existing image/video-quality metrics.
Open AccessMachine vision-aware quality metrics for compressed image and video assessment
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 and recognition, which are integral to video surveillance and autonomous vehicles, involve so much data that they necessitate machine-vision processing with minimal human intervention. In such cases, the video codec must be optimized for machine vision. This paper explores the effects of compression on detection and recognition algorithms (objects, faces, and license plates) and introduces novel full-reference image/video-quality metrics for each task, tailored to machine vision. Experimental results indicate our proposed metrics correlate better with the machine-vision results for the respective tasks than do existing image/video-quality metrics.
- Open Access
AIM 2024 Challenge on Video Super-Resolution Quality Assessment: Methods and Results
This paper presents the Video Super-Resolution (SR) Quality Assessment (QA) Challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024. The task of this challenge was to develop an objective QA method for videos upscaled 2x and 4x by modern image- and video-SR algorithms. QA methods were evaluated by comparing their output with aggregate subjective scores collected from >150,000 pairwise votes obtained through crowd-sourced comparisons across 52 SR methods and 1124 upscaled videos. The goal was to advance the state-of-the-art in SR QA, which had proven to be a challenging problem with limited applicability of traditional QA methods. The challenge had 29 registered participants, and 5 teams had submitted their final results, all outperforming the current state-of-the-art. All data, including the private test subset, has been made publicly available on the challenge homepage at https://challenges.videoprocessing.ai/challenges/super-resolution-metrics-challenge.html
Open AccessAIM 2024 Challenge on Video Super-Resolution Quality Assessment: Methods and Results
This paper presents the Video Super-Resolution (SR) Quality Assessment (QA) Challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024. The task of this challenge was to develop an objective QA method for videos upscaled 2x and 4x by modern image- and video-SR algorithms. QA methods were evaluated by comparing their output with aggregate subjective scores collected from >150,000 pairwise votes obtained through crowd-sourced comparisons across 52 SR methods and 1124 upscaled videos. The goal was to advance the state-of-the-art in SR QA, which had proven to be a challenging problem with limited applicability of traditional QA methods. The challenge had 29 registered participants, and 5 teams had submitted their final results, all outperforming the current state-of-the-art. All data, including the private test subset, has been made publicly available on the challenge homepage at https://challenges.videoprocessing.ai/challenges/super-resolution-metrics-challenge.html
- 15 March 2022
- Published by Elsevier in Digital Signal Processing
- Vol. 126
Temporally coherent person matting trained on fake-motion dataset
- 15 March 2022
- Published by Elsevier in Digital Signal Processing
- Vol. 126
Temporally coherent person matting trained on fake-motion dataset
- Open Access
- 1 January 2022
- Published by Keldysh Institute of Applied Mathematics in Keldysh Institute Preprints
- No. 81,p. 1-24
Compressed Video Quality Assessment for Super-Resolution: A Benchmark and a Quality Metric
We developed a super-resolution (SR) benchmark to analyze SR capabilities to upscale compressed videos. The dataset for the benchmark was collected using video codecs of 5 different compression standards. We assessed 17 state-of-the-art SR models using our benchmark and evaluated their ability to preserve scene context and their robustness to compression artifacts. To get an accurate perceptual ranking of SR models, we conducted a crowd-sourced side-by-side comparison of SR results. We also analyzed the results of the benchmark and developed an objective quality assessment metric based on existing best-performing objective metrics. Our metric outperforms other video quality metrics by Spearman correlation with subjective scores for the task of upscaling compressed videos.
- 1 January 2022
- Published by Keldysh Institute of Applied Mathematics in Keldysh Institute Preprints
- No. 81,p. 1-24
Open AccessCompressed Video Quality Assessment for Super-Resolution: A Benchmark and a Quality Metric
We developed a super-resolution (SR) benchmark to analyze SR capabilities to upscale compressed videos. The dataset for the benchmark was collected using video codecs of 5 different compression standards. We assessed 17 state-of-the-art SR models using our benchmark and evaluated their ability to preserve scene context and their robustness to compression artifacts. To get an accurate perceptual ranking of SR models, we conducted a crowd-sourced side-by-side comparison of SR results. We also analyzed the results of the benchmark and developed an objective quality assessment metric based on existing best-performing objective metrics. Our metric outperforms other video quality metrics by Spearman correlation with subjective scores for the task of upscaling compressed videos.
- Open Access
- 1 January 2022
- Published by Keldysh Institute of Applied Mathematics in Keldysh Institute Preprints
- No. 80,p. 1-13
Combining contrastive and supervised learning for video super-resolution detection
Upscaled video detection is a helpful tool in multimedia forensics, but it’s a challenging task that involves various upscaling and compression algorithms. There are many resolution-enhancement methods, including interpolation and deep-learning based super-resolution, and they leave unique traces. This paper proposes a new upscaled-resolution-detection method based on learning of visual representations using contrastive and cross-entropy losses. To explain how the method detects videos, the major components of our framework are systematically reviewed — in particular, it is shown that most data-augmentation approaches hinder the learning of the method. Through extensive experiments on various datasets, our method has been shown to effectively detects upscaling even in compressed videos and outperforms the state-of-theart alternatives. The code and models are publicly available at https://github.com/msu-video-group/SRDM.
- 1 January 2022
- Published by Keldysh Institute of Applied Mathematics in Keldysh Institute Preprints
- No. 80,p. 1-13
Open AccessCombining contrastive and supervised learning for video super-resolution detection
Upscaled video detection is a helpful tool in multimedia forensics, but it’s a challenging task that involves various upscaling and compression algorithms. There are many resolution-enhancement methods, including interpolation and deep-learning based super-resolution, and they leave unique traces. This paper proposes a new upscaled-resolution-detection method based on learning of visual representations using contrastive and cross-entropy losses. To explain how the method detects videos, the major components of our framework are systematically reviewed — in particular, it is shown that most data-augmentation approaches hinder the learning of the method. Through extensive experiments on various datasets, our method has been shown to effectively detects upscaling even in compressed videos and outperforms the state-of-theart alternatives. The code and models are publicly available at https://github.com/msu-video-group/SRDM.