Automatic Tuning of Denoising Algorithms Parameters without Ground Truth

Arthur Floquet (1) , Sayantan Dutta (1, 2, 3) , Emmanuel Soubies (4) , Duong-Hung Pham (1) , Denis Kouamé (1) , Denis Kouame

1 IRIT-MINDS - CoMputational imagINg anD viSion
2 ICQ - Cohérence Quantique (LPT)
3 LPT - Laboratoire de Physique Théorique
4 IRIT-SC - Signal et Communications

Denoising is omnipresent in image processing. It is usually addressed with algorithms relying on a set of hyperparameters that control the quality of the recovered image. Manual tuning of those parameters can be a daunting task, which calls for the development of automatic tuning methods. Given a denoising algorithm, the best set of parameters is the one that minimizes the error between denoised and ground-truth images. Clearly, this ideal approach is unrealistic, as the ground-truth images are unknown in practice. In this work, we propose unsupervised cost functions — i.e., that only require the noisy image — that allow us to reach this ideal gold standard performance. Specifically, the proposed approach makes it possible to obtain an average PSNR output within less than 1% of the best achievable PSNR.

Mots clés: Bilevel optimization; Denoising; Hyper-parameter tuning

Domaines: Traitement du signal et de l'image [eess.SP]

Arthur Floquet, Sayantan Dutta, Emmanuel Soubies, Duong-Hung Pham, Denis Kouamé, et al.. Automatic Tuning of Denoising Algorithms Parameters without Ground Truth. IEEE Signal Processing Letters, 2024, 31, pp.381 - 385. ⟨10.1109/LSP.2024.3354554⟩. ⟨hal-04344047⟩