Romann M. Weber

29 papers A* 6B 1Journal 17Unranked 4
YearRankTypeTitle / Venue / Authors
2025 A* conf
Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models.
ICLR
Seyedmorteza Sadat, Otmar Hilliges, Romann M. Weber
2025 J jnl
Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales.
CoRR
Seyedmorteza Sadat, Tobias Vontobel, Farnood Salehi, Romann M. Weber
2025 J jnl
HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Models.
CoRR
Seyedmorteza Sadat, Farnood Salehi, Romann M. Weber
2025 A* conf
HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling.
SIGGRAPH Asia
Tobias Vontobel, Seyedmorteza Sadat, Farnood Salehi, Romann M. Weber
2025 J jnl
HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling.
CoRR
Tobias Vontobel, Seyedmorteza Sadat, Farnood Salehi, Romann M. Weber
2025 A* conf
No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models.
ICLR
Seyedmorteza Sadat, Manuel Kansy, Otmar Hilliges, Romann M. Weber
2025 — conf
Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion.
SIGGRAPH (Conference Paper Track)
Manuel Kansy, Jacek Naruniec, Christopher Schroers, Markus Gross, Romann M. Weber
2024 A* conf
CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling.
ICLR
Seyedmorteza Sadat, Jakob Buhmann, Derek Bradley, Otmar Hilliges, Romann M. Weber
2024 J jnl
Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models.
CoRR
Seyedmorteza Sadat, Otmar Hilliges, Romann M. Weber
2024 A* conf
LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models.
NeurIPS
Seyedmorteza Sadat, Jakob Buhmann, Derek Bradley, Otmar Hilliges, Romann M. Weber
2024 J jnl
LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models.
CoRR
Seyedmorteza Sadat, Jakob Buhmann, Derek Bradley, Otmar Hilliges, Romann M. Weber
2024 J jnl
No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models.
CoRR
Seyedmorteza Sadat, Manuel Kansy, Otmar Hilliges, Romann M. Weber
2024 J jnl
Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion.
CoRR
Manuel Kansy, Jacek Naruniec, Christopher Schroers, Markus Gross, Romann M. Weber
2023 J jnl
CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling.
CoRR
Seyedmorteza Sadat, Jakob Buhmann, Derek Bradley, Otmar Hilliges, Romann M. Weber
2023 — conf
Controllable Inversion of Black-Box Face Recognition Models via Diffusion.
ICCV (Workshops)
Manuel Kansy, Anton Raël, Graziana Mignone, Jacek Naruniec, Christopher Schroers, Markus Gross, Romann M. Weber
2023 J jnl
Controllable Inversion of Black-Box Face-Recognition Models via Diffusion.
CoRR
Manuel Kansy, Anton Raël, Graziana Mignone, Jacek Naruniec, Christopher Schroers, Markus Gross, Romann M. Weber
2023 B conf
Memories for Virtual AI Characters.
INLG
Fabian Landwehr, Erika Varis Doggett, Romann M. Weber
2023 — conf
Self-Supervised Effective Resolution Estimation with Adversarial Augmentations.
WACV (Workshops)
Manuel Kansy, Julian Balletshofer, Jacek Naruniec, Christopher Schroers, Graziana Mignone, Markus Gross, Romann M. Weber
2023 J jnl
The Score-Difference Flow for Implicit Generative Modeling.
CoRR
Romann M. Weber
2023 J jnl
The Score-Difference Flow for Implicit Generative Modeling.
Trans. Mach. Learn. Res.
Romann M. Weber
2022 J jnl
Deep Adaptive Sampling and Reconstruction Using Analytic Distributions.
ACM Trans. Graph.
Farnood Salehi, Marco Manzi, Gerhard Roethlin, Romann M. Weber, Christopher Schroers, Marios Papas
2022 J jnl
Learning Dynamic 3D Geometry and Texture for Video Face Swapping.
Comput. Graph. Forum
Christopher Otto, Jacek Naruniec, Leonhard Helminger, Thomas Etterlin, Graziana Mignone, Prashanth Chandran, Gaspard Zoss, Christopher Schroers, Markus Gross, Paulo F. U. Gotardo, Derek Bradley, Romann M. Weber
2021 J jnl
The Hidden Tasks of Generative Adversarial Networks: An Alternative Perspective on GAN Training.
CoRR
Romann M. Weber
2020 J jnl
High-Resolution Neural Face Swapping for Visual Effects.
Comput. Graph. Forum
Jacek Naruniec, Leonhard Helminger, Christopher Schroers, Romann M. Weber
2018 J jnl
Disentangled Dynamic Representations from Unordered Data.
CoRR
Leonhard Helminger, Abdelaziz Djelouah, Markus H. Gross, Romann M. Weber
2018 A* conf
InspireMe: Learning Sequence Models for Stories.
AAAI
Vincent Fortuin, Romann M. Weber, Sasha Schriber, Diana Wotruba, Markus H. Gross
2018 — conf
Unsupervised Deep Representations for Learning Audience Facial Behaviors.
CVPR Workshops
Suman Saha, Rajitha Navarathna, Leonhard Helminger, Romann M. Weber
2018 J jnl
Unsupervised Deep Representations for Learning Audience Facial Behaviors.
CoRR
Suman Saha, Rajitha Navarathna, Leonhard Helminger, Romann M. Weber
2013 — —
Discovering optical control strategies : a data-mining approach.
Romann M. Weber