Diffusion Models and Diffusion Posterior Sampling
Recent talk:
-
Inverse Problems in the age of AI
Milan University, May 2025
Main publications:
- D You, PL Dragotti,
INDIGO+: A unified inn-guided probabilistic diffusion algorithm for blind and non-blind image restoration,
IEEE Journal of Selected Topics in Signal Processing 18 (6), 1108-1122
- Andreas Floros, Seyed-Mohsen Moosavi-Dezfooli, Pier Luigi Dragotti, Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution , 39th Annual Conference on Neural Information Processing Systems (NeurIPS), 2025 2019, video
- D Siromani, D You, PL Dragotti
A hallucination metric and correction scheme for diffusion-based image restoration
,
IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP), 2024
- J Chen, D You, D Gündüz, PL Dragotti
CommIN: Semantic image communications as an inverse problem with INN-guided diffusion models
,IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024.
- J. Huang and P.L. Dragotti, WINNet: Wavelet-inspired invertible network for image denoising, IEEE Transactions on Image Processing, 2022