|
Towards explainable image forensics with resampling trace analysis in the Fourier domain| title | Towards explainable image forensics with resampling trace analysis in the Fourier domain |
|---|
| start_date | 2025/03/04 |
|---|
| schedule | 15h-16h |
|---|
| online | no |
|---|
| location_info | salle Maryam Mirzakhani (bât. Borel) |
|---|
| summary | Synthetic image generation methods have recently revolutionized the way in which visual content is created. However, these methods leave traces in the Fourier spectrum, which are invisible to humans but can be effectively detected by specialized tools. More specifically, some of the spectral artifacts are related to the upsampling operations employed in generative models. In this talk, I will first present a semi-white-box method dedicated to detecting synthetic images by revealing the artifacts in the Fourier domain. Then I will present a theoretical study on the artifacts left by general resampling operations, and introduce an unsupervised method that detects the traces of resampling operations in the large sense using an a contrario framework for false alarm control. |
|---|
| responsibles | Leclaire |
|---|
Workflow history| from state (1) | to state | comment | date |
|---|
| submitted | published | | 2025/03/03 13:21 UTC |
| |
|