Test your samples jointly: Pseudo-reference for image quality evaluation - Télécom Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Test your samples jointly: Pseudo-reference for image quality evaluation

Résumé

In this paper, we address the well-known image quality assessment problem but in contrast from existing approaches that predict image quality independently for every images, we propose to jointly model different images depicting the same content to improve the precision of quality estimation. This proposal is motivated by the idea that multiple distorted images can provide information to disambiguate image features related to content and quality. To this aim, we combine the feature representations from the different images to estimate a pseudo-reference that we use to enhance score prediction. Our experiments show that at test-time, our method successfully combines the features from multiple images depicting the same new content, improving estimation quality.

Dates et versions

hal-04205029 , version 1 (12-09-2023)

Identifiants

Citer

Marcelin Tworski, Stéphane Lathuilière. Test your samples jointly: Pseudo-reference for image quality evaluation. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023, Rodes, Greece. ⟨hal-04205029⟩
4 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More