PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 28, 2026Multimedia Tools and Applications1 citationsOpen Access

Deep Self-Supervised Learning Algorithm for Tone-Mapped Image Quality Assessment

Deep self-supervised learning algorithm applied to tone-mapped image quality assessment

View Full Paper

Authors

PPPedro de Carvalho Cayres PintoGNGustavo Martins da Silva NunesFOFernanda D. V. R. Oliveira

Discussion

Loading...

Member takes

Overview

Randomized trial evaluates a new algorithm for image quality assessment, suggesting improved accuracy.

Key Points

  • This research aims to enhance tone-mapped image quality assessment by modifying the Barlow twins algorithm.
  • Adapts Barlow twins algorithm to train CNNs specific for tone-mapped image quality.
  • Employs support vector regression to map quality features extracted from CNNs into an overall quality score.
  • Conducts intra-dataset and cross-dataset experiments using three different image quality databases.
  • Achieves a 1.2% improvement in Pearson correlation coefficient for intra-dataset experiments compared to state-of-the-art.
  • Observes quality assessment improvements of up to 55.2% in cross-dataset experiments.
  • Proposed metrics outperform three existing metrics based on hand-crafted features.
Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Pinto et al. (2026) studied this question.

synapsesocial.com/papers/6a17dbbe3fad632b0f9d87e7https://doi.org/10.1007/s11042-026-21697-6
Ask AI
Helpful
Bookmark
Share
View Full Paper