Stanislav Frolov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Stanislav Frolov has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Andreas Dengel
German Research Center for Artificial Intelligence (DFKI)
10 shared publications - Brian B. Moser
German Research Center for Artificial Intelligence (DFKI)
9 shared publications Federico Raue
German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany
6 shared publications- Federico Raue
German Research Center for Artificial Intelligence (DFKI)
6 shared publications Jörn Hees
German Research Center for Artificial Intelligence (DFKI) Germany
5 shared publications- Sebastian Palacio
German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany
5 shared publications
Latest Publications
- 15 September 2026
- Published by Springer Nature
- p. 295-307
Just Leaf It: Accelerating Diffusion Classifiers with Hierarchical Class Pruning
- 15 September 2026
- Published by Springer Nature
- p. 295-307
Just Leaf It: Accelerating Diffusion Classifiers with Hierarchical Class Pruning
- 14 September 2026
- Published by Springer Nature
- p. 392-404
OA-CutMix: Correcting the Label Bias of CutMix
- 14 September 2026
- Published by Springer Nature
- p. 392-404
OA-CutMix: Correcting the Label Bias of CutMix
- 22 July 2025
- Published by Springer Nature
- p. 316-331
Federated Learning for Blind Image Super-Resolution
- 22 July 2025
- Published by Springer Nature
- p. 316-331
Federated Learning for Blind Image Super-Resolution
- Open Access
- 24 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1162-1176
PromptMap: An Alternative Interaction Style for AI-Based Image Generation
- 24 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1162-1176
Open AccessPromptMap: An Alternative Interaction Style for AI-Based Image Generation
- Top Cited PapersOpen Access
- 29 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (7) , 11793-11813
Diffusion Models, Image Super-Resolution, and Everything: A Survey
Diffusion models (DMs) have disrupted the image super-resolution (SR) field and further closed the gap between image quality and human perceptual preferences. They are easy to train and can produce very high-quality samples that exceed the realism of those produced by previous generative methods. Despite their promising results, they also come with new challenges that need further research: high computational demands, comparability, lack of explainability, color shifts, and more. Unfortunately, entry into this field is overwhelming because of the abundance of publications. To address this, we provide a unified recount of the theoretical foundations underlying DMs applied to image SR and offer a detailed analysis that underscores the unique characteristics and methodologies within this domain, distinct from broader existing reviews in the field. This article articulates a cohesive understanding of DM principles and explores current research avenues, including alternative input domains, conditioning techniques, guidance mechanisms, corruption spaces, and zero-shot learning approaches. By offering a detailed examination of the evolution and current trends in image SR through the lens of DMs, this article sheds light on the existing challenges and charts potential future directions, aiming to inspire further innovation in this rapidly advancing area.
- 29 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (7) , 11793-11813
Top Cited PapersOpen AccessDiffusion Models, Image Super-Resolution, and Everything: A Survey
Diffusion models (DMs) have disrupted the image super-resolution (SR) field and further closed the gap between image quality and human perceptual preferences. They are easy to train and can produce very high-quality samples that exceed the realism of those produced by previous generative methods. Despite their promising results, they also come with new challenges that need further research: high computational demands, comparability, lack of explainability, color shifts, and more. Unfortunately, entry into this field is overwhelming because of the abundance of publications. To address this, we provide a unified recount of the theoretical foundations underlying DMs applied to image SR and offer a detailed analysis that underscores the unique characteristics and methodologies within this domain, distinct from broader existing reviews in the field. This article articulates a cohesive understanding of DM principles and explores current research avenues, including alternative input domains, conditioning techniques, guidance mechanisms, corruption spaces, and zero-shot learning approaches. By offering a detailed examination of the evolution and current trends in image SR through the lens of DMs, this article sheds light on the existing challenges and charts potential future directions, aiming to inspire further innovation in this rapidly advancing area.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 10621-10629
ObjBlur: A Curriculum Learning Approach With Progressive Object-Level Blurring for Improved Layout-to-Image Generation
We present ObjBlur, a novel curriculum learning approach to improve layout-to-image generation models, where the task is to produce realistic images from layouts composed of boxes and labels. Our method, based on progressive object-level blurring, effectively stabilizes training and enhances the quality of generated images. This strategy systematically applies varying degrees of blurring to individual objects or the background during training, starting with strong blurring to progressively cleaner images. Our findings reveal significant performance improvements, stabilized training, smoother convergence, and reduced variance between multiple runs. Moreover, our technique is compatible with generative adversarial networks and diffusion models, highlighting its versatility across generative modeling paradigms. We reach new state-of-the-art results on the complex COCO and Visual Genome datasets.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 10621-10629
Open AccessObjBlur: A Curriculum Learning Approach With Progressive Object-Level Blurring for Improved Layout-to-Image Generation
We present ObjBlur, a novel curriculum learning approach to improve layout-to-image generation models, where the task is to produce realistic images from layouts composed of boxes and labels. Our method, based on progressive object-level blurring, effectively stabilizes training and enhances the quality of generated images. This strategy systematically applies varying degrees of blurring to individual objects or the background during training, starting with strong blurring to progressively cleaner images. Our findings reveal significant performance improvements, stabilized training, smoother convergence, and reduced variance between multiple runs. Moreover, our technique is compatible with generative adversarial networks and diffusion models, highlighting its versatility across generative modeling paradigms. We reach new state-of-the-art results on the complex COCO and Visual Genome datasets.
- Open Access
Federated Learning for Blind Image Super-Resolution
Traditional blind image SR methods need to model real-world degradations precisely. Consequently, current research struggles with this dilemma by assuming idealized degradations, which leads to limited applicability to actual user data. Moreover, the ideal scenario - training models on data from the targeted user base - presents significant privacy concerns. To address both challenges, we propose to fuse image SR with federated learning, allowing real-world degradations to be directly learned from users without invading their privacy. Furthermore, it enables optimization across many devices without data centralization. As this fusion is underexplored, we introduce new benchmarks specifically designed to evaluate new SR methods in this federated setting. By doing so, we employ known degradation modeling techniques from SR research. However, rather than aiming to mirror real degradations, our benchmarks use these degradation models to simulate the variety of degradations found across clients within a distributed user base. This distinction is crucial as it circumvents the need to precisely model real-world degradations, which limits contemporary blind image SR research. Our proposed benchmarks investigate blind image SR under new aspects, namely differently distributed degradation types among users and varying user numbers. We believe new methods tested within these benchmarks will perform more similarly in an application, as the simulated scenario addresses the variety while federated learning enables the training on actual degradations.
Open AccessFederated Learning for Blind Image Super-Resolution
Traditional blind image SR methods need to model real-world degradations precisely. Consequently, current research struggles with this dilemma by assuming idealized degradations, which leads to limited applicability to actual user data. Moreover, the ideal scenario - training models on data from the targeted user base - presents significant privacy concerns. To address both challenges, we propose to fuse image SR with federated learning, allowing real-world degradations to be directly learned from users without invading their privacy. Furthermore, it enables optimization across many devices without data centralization. As this fusion is underexplored, we introduce new benchmarks specifically designed to evaluate new SR methods in this federated setting. By doing so, we employ known degradation modeling techniques from SR research. However, rather than aiming to mirror real degradations, our benchmarks use these degradation models to simulate the variety of degradations found across clients within a distributed user base. This distinction is crucial as it circumvents the need to precisely model real-world degradations, which limits contemporary blind image SR research. Our proposed benchmarks investigate blind image SR under new aspects, namely differently distributed degradation types among users and varying user numbers. We believe new methods tested within these benchmarks will perform more similarly in an application, as the simulated scenario addresses the variety while federated learning enables the training on actual degradations.
- 22 September 2023
- Published by Springer Nature
- p. 232-243
DWA: Differential Wavelet Amplifier for Image Super-Resolution
- 22 September 2023
- Published by Springer Nature
- p. 232-243
DWA: Differential Wavelet Amplifier for Image Super-Resolution
- Open Access
Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
With the advent of Deep Learning (DL), Super-Resolution (SR) has also become a thriving research area. However, despite promising results, the field still faces challenges that require further research e.g., allowing flexible upsampling, more effective loss functions, and better evaluation metrics. We review the domain of SR in light of recent advances, and examine state-of-the-art models such as diffusion (DDPM) and transformer-based SR models. We present a critical discussion on contemporary strategies used in SR, and identify promising yet unexplored research directions. We complement previous surveys by incorporating the latest developments in the field such as uncertainty-driven losses, wavelet networks, neural architecture search, novel normalization methods, and the latests evaluation techniques. We also include several visualizations for the models and methods throughout each chapter in order to facilitate a global understanding of the trends in the field. This review is ultimately aimed at helping researchers to push the boundaries of DL applied to SR.
Open AccessHitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
With the advent of Deep Learning (DL), Super-Resolution (SR) has also become a thriving research area. However, despite promising results, the field still faces challenges that require further research e.g., allowing flexible upsampling, more effective loss functions, and better evaluation metrics. We review the domain of SR in light of recent advances, and examine state-of-the-art models such as diffusion (DDPM) and transformer-based SR models. We present a critical discussion on contemporary strategies used in SR, and identify promising yet unexplored research directions. We complement previous surveys by incorporating the latest developments in the field such as uncertainty-driven losses, wavelet networks, neural architecture search, novel normalization methods, and the latests evaluation techniques. We also include several visualizations for the models and methods throughout each chapter in order to facilitate a global understanding of the trends in the field. This review is ultimately aimed at helping researchers to push the boundaries of DL applied to SR.
- Open Access
- 10 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (8) , 9862-9882
Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
With the advent of Deep Learning (DL), Super-Resolution (SR) has also become a thriving research area. However, despite promising results, the field still faces challenges that require further research, e.g., allowing flexible upsampling, more effective loss functions, and better evaluation metrics. We review the domain of SR in light of recent advances and examine state-of-the-art models such as diffusion (DDPM) and transformer-based SR models. We critically discuss contemporary strategies used in SR and identify promising yet unexplored research directions. We complement previous surveys by incorporating the latest developments in the field, such as uncertainty-driven losses, wavelet networks, neural architecture search, novel normalization methods, and the latest evaluation techniques. We also include several visualizations for the models and methods throughout each chapter to facilitate a global understanding of the trends in the field. This review ultimately aims at helping researchers to push the boundaries of DL applied to SR.
- 10 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (8) , 9862-9882
Open AccessHitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
With the advent of Deep Learning (DL), Super-Resolution (SR) has also become a thriving research area. However, despite promising results, the field still faces challenges that require further research, e.g., allowing flexible upsampling, more effective loss functions, and better evaluation metrics. We review the domain of SR in light of recent advances and examine state-of-the-art models such as diffusion (DDPM) and transformer-based SR models. We critically discuss contemporary strategies used in SR and identify promising yet unexplored research directions. We complement previous surveys by incorporating the latest developments in the field, such as uncertainty-driven losses, wavelet networks, neural architecture search, novel normalization methods, and the latest evaluation techniques. We also include several visualizations for the models and methods throughout each chapter to facilitate a global understanding of the trends in the field. This review ultimately aims at helping researchers to push the boundaries of DL applied to SR.