89 citations · 197 across the 9 of their papers we have counts for
5 papers · 1 filter
Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
Axel Sauer, Frederic Boesel, Tim Dockhorn +3
Diffusion models are the main driver of progress in image and video synthesis, but suffer from slow inference speed. Distillation methods, like the recently introduced adversarial…
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
Patrick Esser, Sumith Kulal, Andreas Blattmann +14
Diffusion models create data from noise by inverting the forward paths of data towards noise and have emerged as a powerful generative modeling technique for high-dimensional, perc…
Adversarial Diffusion Distillation
Axel Sauer, Dominik Lorenz, Andreas Blattmann +1
We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while ma…
Projected GANs Converge Faster
Axel Sauer, Kashyap Chitta, Jens Müller +1
Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train. They need careful regularization, vast amounts of compute, and expensive hyper-para…
Tracking Holistic Object Representations
Axel Sauer, Elie Aljalbout, Sami Haddadin
Recent advances in visual tracking are based on siamese feature extractors and template matching. For this category of trackers, latest research focuses on better feature embedding…