3 papers
cs.CV2024
DepthFM: Fast Monocular Depth Estimation with Flow Matching
Ming Gui, Johannes Schusterbauer, Ulrich Prestel +6
Current discriminative depth estimation methods often produce blurry artifacts, while generative approaches suffer from slow sampling due to curvatures in the noise-to-depth transp…
cs.CV2024
Boosting Latent Diffusion with Flow Matching
Johannes Schusterbauer, Ming Gui, Pingchuan Ma +4
Visual synthesis has recently seen significant leaps in performance, largely due to breakthroughs in generative models. Diffusion models have been a key enabler, as they excel in i…
cs.CV2024
ZigMa: A DiT-style Zigzag Mamba Diffusion Model
Vincent Tao Hu, Stefan Andreas Baumann, Ming Gui +4
The diffusion model has long been plagued by scalability and quadratic complexity issues, especially within transformer-based structures. In this study, we aim to leverage the long…