English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Stereoscopic image quality measurement (SIQM) has become increasinglyimportant for guiding stereo image processing and commutation systems due tothe widespread usage of 3D contents. Compared with conventional methods whichare relied on hand-crafted features, deep learning oriented measurements haveachieved remarkable performance in recent years. However, most existing deepSIQM evaluators are not specifically built for stereoscopic contents andconsider little prior domain knowledge of the 3D human visual system (HVS) innetwork design. In this paper, we develop a Predictive Auto-encoDing Network(PAD-Net) for blind/No-Reference stereoscopic image quality measurement. In thefirst stage, inspired by the predictive coding theory that the cognition systemtries to match bottom-up visual signal with top-down predictions, we adopt theencoder-decoder architecture to reconstruct the distorted inputs. Besides,motivated by the binocular rivalry phenomenon, we leverage the likelihood andprior maps generated from the predictive coding process in the Siameseframework for assisting SIQM. In the second stage, quality regression networkis applied to the fusion image for acquiring the perceptual quality prediction.The performance of PAD-Net has been extensively evaluated on three benchmarkdatabases and the superiority has been well validated on both symmetrically andasymmetrically distorted stereoscopic images under various distortion types.

Binocular Rivalry Oriented Predictive Auto-Encoding Network for Blind Stereoscopic Image Quality Measurement