3 papers
cs.CV2025
Deep priors for satellite image restoration with accurate uncertainties
Biquard Maud, Marie Chabert, Florence Genin +2
Satellite optical images, upon their on-ground receipt, offer a distorted view of the observed scene. Their restoration, including denoising, deblurring, and sometimes super-resolu…
cs.CV2025
Variational Bayes image restoration with compressive autoencoders
Maud Biquard, Marie Chabert, Florence Genin +2
Regularization of inverse problems is of paramount importance in computational imaging. The ability of neural networks to learn efficient image representations has been recently ex…
cs.CV2025
PG-DPIR: An efficient plug-and-play method for high-count Poisson-Gaussian inverse problems
Maud Biquard, Marie Chabert, Florence Genin +2
Poisson-Gaussian noise describes the noise of various imaging systems thus the need of efficient algorithms for Poisson-Gaussian image restoration. Deep learning methods offer stat…