End-to-end Interpretable Learning of Non-blind Image Deblurring - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

End-to-end Interpretable Learning of Non-blind Image Deblurring

Résumé

Non-blind image deblurring is typically formulated as a linear least-squares problem regularized by natural priors on the corresponding sharp picture's gradients, which can be solved, for example, using a half-quadratic splitting method with Richardson fixed-point iterations for its least-squares updates and a proximal operator for the auxiliary variable updates. We propose to precondition the Richardson solver using approximate inverse filters of the (known) blur and natural image prior kernels. Using convolutions instead of a generic linear preconditioner allows extremely efficient parameter sharing across the image, and leads to significant gains in accuracy and/or speed compared to classical FFT and conjugate-gradient methods. More importantly, the proposed architecture is easily adapted to learning both the preconditioner and the proximal operator using CNN embeddings. This yields a simple and efficient algorithm for non-blind image deblurring which is fully interpretable, can be learned end to end, and whose accuracy matches or exceeds the state of the art, quite significantly, in the non-uniform case.
Fichier principal
Vignette du fichier
2007.01769.pdf (1.77 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02966204 , version 1 (13-10-2020)

Identifiants

Citer

Thomas Eboli, Jian Sun, Jean Ponce. End-to-end Interpretable Learning of Non-blind Image Deblurring. ECCV 2020 - 16th European Conference on Computer Vision, Aug 2020, Glasgow / Virtual, United Kingdom. ⟨hal-02966204⟩
77 Consultations
98 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More