2 papers
eess.IV2024
Lightweight Video Denoising Using a Classic Bayesian Backbone
Clément Bled, François Pitié
In recent years, state-of-the-art image and video denoising networks have become increasingly large, requiring millions of trainable parameters to achieve best-in-class performance…
eess.IV2023
Pushing The Limits of the Wiener Filter in Image Denoising
Clément Bled, François Pitié
As modern image denoiser networks have grown in size, their reported performance in popular real noise benchmarks such as DND and SIDD have now long outperformed classic non-deep l…