AI RESEARCH
SHAMISA: SHAped Modeling of Implicit Structural Associations for Self-supervised No-Reference Image Quality Assessment
arXiv CS.AI
•
ArXi:2603.13669v1 Announce Type: cross No-Reference Image Quality Assessment (NR-IQA) aims to estimate perceptual quality without access to a reference image of pristine quality. Learning an NR-IQA model faces a fundamental bottleneck: its need for a large number of costly human perceptual labels. We propose SHAMISA, a non-contrastive self-supervised framework that learns from unlabeled distorted images by leveraging explicitly structured relational supervision. Unlike prior methods that impose rigid, binary similarity constraints.