Stanislav Frolov

Hi, I'm a 4th year Ph.D. student at RPTU Kaiserslautern and German Research Center for Artificial Intelligence, advised by Andreas Dengel.

My main interests are computer vision and machine learning. I use deep generative models for controlled image synthesis.

In 2021, I interned at Adobe Research working with Kushal Kafle, Scott Cohen and Tobias Hinz on image editing. In 2022, I interned at Meta AI working with Adriana Romero-Soriano, Michał Drożdżal and Jakob Verbeek on spherical image generation.

Previously, I've worked at inovex as a data engineer, and completed my B.Sc. and M.Sc degrees in Electrical Engineering at the Karlsruhe Institute of Technology.

If you are interested in similar topics, want to chat or collaborate, feel free to contact me.

Email / Google Scholar / LinkedIn / GitHub / Twitter

Research Internships


Meta 2022 Paris	Adobe 2021 Remote

News

[07/2024] Our SpotDiffusion paper got accepted to WACV 2025 in the first round.
[07/2024] New paper: SpotDiffusion produces fast seamless panoramas via shifted denoising windows over time.
[07/2024] Our ObjBlur paper got accepted to ACM Multimedia 2024.
[04/2024] New paper: Federated Super-Resolution studies distributed degradations among varying user numbers.
[04/2024] New paper: ObjBlur uses progressive object-level blurring to improve L2I models.
[03/2024] New paper: LD3M proposes latent dataset distillation with diffusion models.
[01/2024] New Survey on Diffusion Models for Super-Resolution is online.
[08/2023] New paper: YODA uses dynamic attention-guided diffusion for SR.
[07/2023] New paper: Differential Wavelet Amplifier got accepted to ICANN 2023.
[06/2023] Our impact of image compression study got accepted at the ICML workshop on neural compression.
[04/2023] New paper: DiWa uses wavelets to improve diffusion-based SR.
[02/2023] Our Super-Resolution Survey paper got accepted to TPAMI.
[08/2022] Started research internship at Meta AI in Paris working on 360° image generation.
[07/2022] Our DT2I paper got accepted to ICANN 2022.

Publications

	SpotDiffusion: A Fast Approach For Seamless Panorama Generation Over Time Stanislav Frolov, Brian B. Moser, Andreas Dengel WACV, 2025 project page, code
	Federated Learning for Blind Image Super-Resolution Brian B. Moser, Ahmed Anwar, Federico Raue, Stanislav Frolov, Andreas Dengel ICONIP, 2024
	ObjBlur: A Curriculum Learning Approach with Progressive Object-Level Blurring for Improved Layout-to-Image Generation Stanislav Frolov, Brian B. Moser, Sebastian Palacio, Andreas Dengel ACM Multimedia, 2024
	Latent Dataset Distillation with Diffusion Models Brian B. Moser, Federico Raue, Sebastian Palacio, Stanislav Frolov, Andreas Dengel arXiv, 2024
	Diffusion Models, Image Super-Resolution And Everything: A Survey Brian B. Moser, Arundhati S. Shanbhag, Federico Raue, Stanislav Frolov, Sebastian Palacio, Andreas Dengel TNNLS, 2024
	YODA: Dynamic Attention-Guided Diffusion for Image Super-Resolution Brian Moser, Stanislav Frolov, Federico Raue, Sebastian Palacio, Andreas Dengel arXiv, 2023
	DWA: Differential Wavelet Amplifier for Image Super-Resolution Brian Moser, Stanislav Frolov, Federico Raue, Sebastian Palacio, Andreas Dengel ICANN, 2023
	Are Visual Recognition Models Robust to Image Compression? João Maria Janeiro, Stanislav Frolov, Alaaeldin El-Nouby, Jakob Verbeek ICML Workshop on Neural Compression, 2023
	Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolution Brian Moser, Stanislav Frolov, Federico Raue, Sebastian Palacio, Andreas Dengel IJCNN, 2024
	Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances Brian Moser, Federico Raue, Stanislav Frolov, Jörn Hees, Sebastian Palacio, Andreas Dengel TPAMI, 2023 project page
	DT2I: Dense Text-to-Image Generation from Region Descriptions Stanislav Frolov, Prateek Bansal, Jörn Hees, Andreas Dengel ICANN, 2022
	Combining Transformer Generators with Convolutional Discriminators Ricard Durall, Stanislav Frolov, Jörn Hees, Federico Raue, Franz-Josef Pfreundt, Andreas Dengel, Janis Keuper GCAI, 2021
	AttrLostGAN: Attribute Controlled Image Synthesis from Reconfigurable Layout and Style Stanislav Frolov, Avneesh Sharma, Jörn Hees, Tushar Karayil, Federico Raue, Andreas Dengel GCPR, 2021 code
	Adversarial Text-to-Image Synthesis: A Review Stanislav Frolov, Tobias Hinz, Federico Raue, Jörn Hees, Andreas Dengel Neural Networks Journal, 2021
	Hybrid-S2S: Video Object Segmentation with Recurrent Networks and Correspondence Matching Fatemeh Azimi, Stanislav Frolov, Federico Raue, Jörn Hees, Andreas Dengel VISIGRAPP, 2021 code
	Leveraging Visual Question Answering to Improve Text-to-Image Synthesis Stanislav Frolov, Shailza Jolly, Jörn Hees, Andreas Dengel LANTERN Workshop at COLING, 2020 slides

Reviewing Since

Conference: CVPR'23, ICLR'23, NeurIPS'23, AAAI'24, ECCV'24, WACV'21, ACMMM'24, ICANN'22, GCAI'21, GCPR'21, DAS'20
Workshop: LANTERN'21
Journal: APIN'21

Template by Jon Barron