|
Plug-and-Play methods: theory and practice| title | Plug-and-Play methods: theory and practice |
|---|
| start_date | 2025/05/06 |
|---|
| schedule | 14h-16h |
|---|
| online | no |
|---|
| location_info | salle Maryam Mirzakhani (bât. Borel) |
|---|
| summary | In image restoration, PnP methods leverage the strength of trainable denoisers by integrating them in existing optimization schemes. First, we will show how to leverage generative models to create new denoisers. Specifically, we introduce the PnP Flow algorithm, a PnP method based on Flow Matching. In the second part of the talk, we will study desirable properties of PnP denoisers that ensure convergence of the associated iterative schemes. In particular, we provide an in-depth study of necessary and sufficient conditions for a neural network to be convex, beyond the traditional Input Convex Neural Network (ICNN) architecture |
|---|
| responsibles | Leclaire |
|---|
Workflow history| from state (1) | to state | comment | date |
|---|
| submitted | published | | 2025/04/29 12:31 UTC |
| |
|