No-Reference Image Quality Assessment by Hallucinating Pristine Features

Chen, Baoliang; Zhu, Lingyu; Kong, Chenqi; Zhu, Hanwei; Wang, Shiqi; Zhu, Li

doi:10.48550/arxiv.2108.04165

Cited by 1 publication

(1 citation statement)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Third, the assumption that HVS is highly adapted to the natural scene has been a golden hypothesis in no-reference IQA. Due to the unavailability of the pristine images, the visual quality is quantified from the perspectives that how those regularities are modified along with the distortion [3]. The FR-IQA methods, which shall be understood as the fidelity measurement, typically do not rely on distributions.…”

Section: Connections With Existing Modelsmentioning

confidence: 99%

DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space

Liao,

Chen,

Zhu

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Existing deep learning-based full-reference IQA (FR-IQA) models usually predict the image quality in a deterministic way by explicitly comparing the features, gauging how severely distorted an image is by how far the corresponding feature lies from the space of the reference images. Herein, we look at this problem from a different viewpoint and propose to model the quality degradation in perceptual space from a statistical distribution perspective. As such, the quality is measured based upon the Wasserstein distance in the deep feature domain. More specifically, the 1D Wasserstein distance at each stage of the pre-trained VGG network is measured, based on which the final quality score is performed. The deep Wasserstein distance (DeepWSD) performed on features from neural networks enjoys better interpretability of the quality contamination caused by various types of distortions and presents an advanced quality prediction capability. Extensive experiments and theoretical analysis show the superiority of the proposed DeepWSD in terms of both quality prediction and optimization. The implementation of our method is publicly available at https://github.com/Buka-Xing/DeepWSD.

show abstract

Section: Connections With Existing Modelsmentioning

confidence: 99%