5 citations · 11 across the 14 of their papers we have counts for
16 papers
Reviving ConvNeXt for Efficient Convolutional Diffusion Models
Taesung Kwon, Lorenzo Bianchi, Lennart Wittke +5
Recent diffusion models increasingly favor Transformer backbones, motivated by the remarkable scalability of fully attentional architectures. Yet the locality bias, parameter effic…
HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Models
Seyedmorteza Sadat, Farnood Salehi, Romann M. Weber
While diffusion models have made remarkable progress in image generation, their outputs can still appear unrealistic and lack fine details, especially when using fewer number of ne…
HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling
Tobias Vontobel, Seyedmorteza Sadat, Farnood Salehi +1
Diffusion models have emerged as the leading approach for image synthesis, demonstrating exceptional photorealism and diversity. However, training diffusion models at high resoluti…
Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales
Seyedmorteza Sadat, Tobias Vontobel, Farnood Salehi +1
Classifier-free guidance (CFG) has become an essential component of modern conditional diffusion models. Although highly effective in practice, the underlying mechanisms by which C…
Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models
Seyedmorteza Sadat, Otmar Hilliges, Romann M. Weber
Classifier-free guidance (CFG) is crucial for improving both generation quality and alignment between the input condition and final output in diffusion models. While a high guidanc…
Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion
Manuel Kansy, Jacek Naruniec, Christopher Schroers +2
Recent years have seen a tremendous improvement in the quality of video generation and editing approaches. While several techniques focus on editing appearance, few address motion.…
No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models
Seyedmorteza Sadat, Manuel Kansy, Otmar Hilliges +1
Classifier-free guidance (CFG) has become the standard method for enhancing the quality of conditional diffusion models. However, employing CFG requires either training an uncondit…
LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models
Seyedmorteza Sadat, Jakob Buhmann, Derek Bradley +2
Advances in latent diffusion models (LDMs) have revolutionized high-resolution image generation, but the design space of the autoencoder that is central to these systems remains un…
CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling
Seyedmorteza Sadat, Jakob Buhmann, Derek Bradley +2
While conditional diffusion models are known to have good coverage of the data distribution, they still face limitations in output diversity, particularly when sampled with a high…
The Score-Difference Flow for Implicit Generative Modeling
Romann M. Weber
Implicit generative modeling (IGM) aims to produce samples of synthetic data matching the characteristics of a target data distribution. Recent work (e.g. score-matching networks,…
Controllable Inversion of Black-Box Face Recognition Models via Diffusion
Manuel Kansy, Anton Raël, Graziana Mignone +4
Face recognition models embed a face image into a low-dimensional identity vector containing abstract encodings of identity-specific facial features that allow individuals to be di…
Exploiting the Hidden Tasks of GANs: Making Implicit Subproblems Explicit
Romann M. Weber
We present an alternative perspective on the training of generative adversarial networks (GANs), showing that the training step for a GAN generator decomposes into two implicit sub…
Spectrogram Feature Losses for Music Source Separation
Abhimanyu Sahai, Romann Weber, Brian McWilliams
In this paper we study deep learning-based music source separation, and explore using an alternative loss to the standard spectrogram pixel-level L2 loss for model training. Our ma…
Disentangled Dynamic Representations from Unordered Data
Leonhard Helminger, Abdelaziz Djelouah, Markus Gross +1
We present a deep generative model that learns disentangled static and dynamic representations of data from unordered input. Our approach exploits regularities in sequential data t…
Unsupervised Deep Representations for Learning Audience Facial Behaviors
Suman Saha, Rajitha Navarathna, Leonhard Helminger +1
In this paper, we present an unsupervised learning approach for analyzing facial behavior based on a deep generative model combined with a convolutional neural network (CNN). We jo…
Beyond Spikes: Neural Codes and the Chemical Vocabulary of Cognition
Romann M. Weber
In this paper, I examine what I refer to as the spike doctrine, which is the generally held belief in neuroscience that information in the brain is encoded by sequences of neural a…