| ZigMa: A DiT-style Zigzag Mamba Diffusion Model VT Hu, SA Baumann, M Gui, O Grebenkova, P Ma, J Fischer, B Ommer European Conference on Computer Vision (ECCV) 2024, 2024 | 73* | 2024 |
| Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers K Crowson*, SA Baumann*, A Birch*, TM Abraham, DZ Kaplan, ... Forty-first International Conference on Machine Learning, 2024 | 33 | 2024 |
| DepthFM: Fast monocular depth estimation with flow matching M Gui, J Schusterbauer, U Prestel, P Ma, D Kotovenko, O Grebenkova, ... arXiv preprint arXiv:2403.13788, 2024 | 24 | 2024 |
| FMBoost: Boosting Latent Diffusion with Flow Matching J Schusterbauer, M Gui, P Ma, N Stracke, SA Baumann, VT Hu, B Ommer European Conference on Computer Vision, 338-355, 2024 | 7* | 2024 |
| CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models N Stracke, SA Baumann, JM Susskind, MA Bautista, B Ommer European Conference on Computer Vision (ECCV) 2024, 2024 | 4 | 2024 |
| Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions SA Baumann, F Krause, M Neumayr, N Stracke, VT Hu, B Ommer arXiv preprint arXiv:2403.17064, 2024 | 3 | 2024 |
| Deeper Convolutional Neural Networks and Broad Augmentation Policies Improve Performance in Musical Key Estimation SA Baumann Proceedings of the International Society for Music Information Retrieval …, 2021 | 2 | 2021 |
| CleanDIFT: Diffusion Features without Noise N Stracke*, SA Baumann*, K Bauer*, F Fundel, B Ommer arXiv preprint arXiv:2412.03439, 2024 | 1 | 2024 |
| Deep learning-enabled real time in-site quality inspection based on gesture classification IM Sarivan, SA Baumann, DD Álvarez, F Euteneuer, M Reichenbach, ... Advances in Automotive Production Technology–Theory and Application …, 2021 | 1 | 2021 |
| Verfahren zur Überprüfung mindestens eines durch eine Person durchgeführten manuellen Arbeitsschritts IM Sarivan, O Madsen, F Euteneuer, DD Alvarez, SA Baumann, ... DE Patent 102020006056A1, 2021 | | 2021 |
Björn OmmerProfessor, Computer Vision & Learning Group (CompVis), University of MunichVerified email at lmu.de
