REQA: Coarse-to-fine Assessment of Image Quality to Alleviate the Range Effect
Bingheng Li, Fushuo Huo

TL;DR
This paper introduces a coarse-to-fine image quality assessment method that reduces the range effect by combining rank-and-gradient loss with multi-level tolerance loss in a feedback network, improving prediction consistency.
Contribution
It proposes a novel coarse-to-fine assessment framework with specialized loss functions and a feedback network to effectively mitigate the range effect in blind image quality assessment.
Findings
Reduces the range effect compared to state-of-the-art methods.
Improves correlation between predicted and subjective quality scores.
Enhances feature representation through feedback and multi-scale processing.
Abstract
Blind image quality assessment (BIQA) of user generated content (UGC) suffers from the range effect which indicates that on the overall quality range, mean opinion score (MOS) and predicted MOS (pMOS) are well correlated; focusing on a particular range, the correlation is lower. The reason for the range effect is that the predicted deviations both in a wide range and in a narrow range destroy the uniformity between MOS and pMOS. To tackle this problem, a novel method is proposed from coarse-grained metric to fine-grained prediction. Firstly, we design a rank-and-gradient loss for coarse-grained metric. The loss keeps the order and grad consistency between pMOS and MOS, thereby reducing the predicted deviation in a wide range. Secondly, we propose multi-level tolerance loss to make fine-grained prediction. The loss is constrained by a decreasing threshold to limite the predicted…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage and Video Quality Assessment · Advanced Image Fusion Techniques · Visual Attention and Saliency Detection
