About me

Born in 1995 in Kaiserslautern, Germany, with Thai and German roots, my passion for science and computers began early. I aspired to be a Computer Scientist, drawn to the captivating world of coding and problem-solving.

I am currently a Researcher at the German Research Institute for Artificial Intelligence (DFKI) located in Kaiserslautern, Germany. My research is dedicated to pushing the boundaries of strongly-conditional generative AI, addressing complex tasks related to image enhancement and restoration. Additionally, my work extends into the areas of Dataset Distillation and Coreset Selection, aiming to develop efficient methodologies for reducing and optimizing datasets for deep learning applications. Also, I teach “Image Generation and Enhancement” at the University of Kaiserslautern.

My research has been published in prominent AI conferences and journals, including CVPR, WACV, IEEE TPAMI, IEEE ICIP, ACM Multimedia, IEEE TNNLS, etc. I’m passionate about contributing innovative solutions to AI challenges and always keen to collaborate on projects that leverage generative models, dataset optimization, and advanced machine learning techniques.

List of publications

CVPR 2025
sym

2025 - TKG-DM: Training-free Chroma Key Content Generation Diffusion Model

Ryugo Morita, Stanislav Frolov, Brian B. Moser, Takahiro Shirakawa, Ko Watanabe, Andreas Dengel, Jinjia Zhou

WACV 2025
sym

2025 - Dynamic Attention-Guided Diffusion for Image Super-Resolution

Brian B. Moser, Stanislav Frolov, Federico Raue, Sebastian Palacio, Andreas Dengel

WACV 2025
sym

2025 - SpotDiffusion: A Fast Approach For Seamless Panorama Generation Over Time

Stanislav Frolov, Brian B. Moser, Andreas Dengel

Project Site

IEEE ICIP 2025
sym

2025 - When 512x512 Is Not Enough: Local Degradation-Aware Multi-Diffusion for Extreme Image Super-Resolution

Brian B. Moser, Stanislav Frolov, Tobias Nauen, Federico Raue, Andreas Dengel

ACM ETRA 2025 (Best Short Paper Award)
sym

2025 - PupilSense: A Novel Application for Webcam-Based Pupil Diameter Esti- mation

Vijul Shah, Ko Watanabe, Brian B. Moser, Andreas Dengel

Project Site

IJCNN 2025
sym

2025 - Distill the Best, Ignore the Rest: Improving Dataset Distillation with Loss-Value-Based Pruning

Brian B. Moser, Federico Raue, Tobias Nauen, Stanislav Frolov, Andreas Dengel

Project Site

IGARSS 2025
sym

2025 - Multi-Label Scene Classification in Remote Sensing Benefits from Image Super-Resolution

Ashitha Mudraje, Brian B. Moser, Stanislav Frolov, Andreas Dengel

TNNLS 2024
sym

2024 - Diffusion Models, Image Super-Resolution and Everything: A Survey

Brian B. Moser, Arundhati S. Shanbhag, Federico Raue, Stanislav Frolov, Sebastian Palacio, Andreas Dengel

ICAART 2024
sym

2024 - Webcam-based Pupil Diameter Prediction Benefits from Upscaling

Vijul Shah, Brian B. Moser, Ko Watanabe, Andreas Dengel

Project Site

ACM Multimedia 2024
sym
ICONIP 2024
sym

2024 - Federated Learning for Blind Image Super-Resolution

Brian B. Moser, Ahmed Anwar, Federico Raue, Stanislav Frolov, Andreas Dengel

FLTA 2024
sym

2024 - FedAD-Bench: A Unified Benchmark for Federated Unsupervised Anomaly Detection in Tabular Data

Ahmed Anwar, Brian B. Moser, Dayananda Herurkar, Federico Raue, Vinit Hegiste, Tatjana Legler, Andreas Dengel

IJCNN 2024
sym

2024 - Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolution

Brian B. Moser, Stanislav Frolov, Federico Raue, Sebastian Palacio, Andreas Dengel

Project Site

ICANN 2024
sym

2024 - A Study in Dataset Pruning for Image Super-Resolution

Brian B. Moser, Federico Raue, Andreas Dengel

Project Site

ICANN 2023
sym

2023 - DWA: Differential Wavelet Amplifier for Image Super-Resolution

Brian B. Moser, Stanislav Frolov, Federico Raue, Sebastian Palacio, Andreas Dengel

Project Site

ISSEP 2023
sym

2023 - Bridging the Gap: Infusing Natural Science Classes with Computer Science Concepts and Skills

Elena Yanakieva, Annette Bieniusa, Thomas Becka, Brian B. Moser, Dominik Jerger, Christoph Thyssen

TPAMI 2023
sym

2023 - Hitchhiker’s Guide to Super-Resolution: Introduction and Recent Advances

Brian B. Moser, Federico Raue, Stanislav Frolov, Sebastian Palacio, Jörn Hees, Andreas Dengel

Project Site

CVPR NAS Workshop 2022
sym

2022 - Less Is More: Proxy Datasets in NAS Approaches

Brian B. Moser, Federico Raue, Jörn Hees, Andreas Dengel

Project Site

ICANN 2020
sym

2020 - DartsReNet: Exploring New RNN Cells in ReNet Architectures

Brian B. Moser, Federico Raue, Jörn Hees, Andreas Dengel

ICANN 2019
sym

2019 - Comparison Between U-Net and U-ReNet Models in OCR Tasks

Brian B. Moser, Federico Raue, Jörn Hees, Andreas Dengel

Educations

  • 2021 - today, PhD, TU Kaiserslautern / RPTU Kaiserslautern-Landau, Germany
  • 2018 - 2021, Computer Science, M.Sc., TU Kaiserslautern, Germany
  • 2014 - 2018, Computer Science, B.Sc., TU Kaiserslautern, Germany