activity
20242026
collaborators

6 papers

cs.CV2026

Probabilistic Precipitation Nowcasting with Rectified Flow Transformers

Johannes Schusterbauer, Jannik Wiese, Nick Stracke +2

Accurate weather forecasts are essential across various domains and are safety-critical in extreme weather conditions. Compared to simulation-based forecasting, data-driven approac…

cs.CV2026

Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation

Johannes Schusterbauer, Ming Gui, Yusong Li +3

Diffusion- and flow-based models usually allocate compute uniformly across space, updating all patches with the same timestep and number of function evaluations. While convenient,…

cs.CV2026

Adapting Self-Supervised Representations as a Latent Space for Efficient Generation

Ming Gui, Johannes Schusterbauer, Timy Phan +4

We introduce Representation Tokenizer (RepTok), a generative modeling framework that represents an image using a single continuous latent token obtained from self-supervised vision…

cs.CV2025

SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models

Pingchuan Ma, Xiaopei Yang, Yusong Li +4

Explicitly disentangling style and content in vision models remains challenging due to their semantic overlap and the subjectivity of human perception. Existing methods propose sep…

cs.CV2025

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment

Johannes Schusterbauer, Ming Gui, Frank Fundel +1

Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, curren…

cs.CV2024

Distillation of Diffusion Features for Semantic Correspondence

Frank Fundel, Johannes Schusterbauer, Vincent Tao Hu +1

Semantic correspondence, the task of determining relationships between different parts of images, underpins various applications including 3D reconstruction, image-to-image transla…