Deep Decomposition and Bilinear Pooling Network for Blind Night-Time Image Quality Evaluation

TL;DR

This paper introduces DDB-Net, a deep neural network that decomposes night-time images into illumination and reflection components, then encodes and pools features for improved blind image quality assessment of challenging night-time images.

Contribution

It proposes a novel deep decomposition and bilinear pooling network specifically designed for blind night-time image quality evaluation, addressing complex authentic distortions.

Findings

DDB-Net outperforms existing BIQA methods on benchmark datasets.

The decomposition approach effectively isolates degradation factors.

Bilinear pooling enhances the quality prediction accuracy.

Abstract

Blind image quality assessment (BIQA), which aims to accurately predict the image quality without any pristine reference information, has been extensively concerned in the past decades. Especially, with the help of deep neural networks, great progress has been achieved. However, it remains less investigated on BIQA for night-time images (NTIs) which usually suffers from complicated authentic distortions such as reduced visibility, low contrast, additive noises, and color distortions. These diverse authentic degradations particularly challenges the design of effective deep neural network for blind NTI quality evaluation (NTIQE). In this paper, we propose a novel deep decomposition and bilinear pooling network (DDB-Net) to better address this issue. The DDB-Net contains three modules, i.e., an image decomposition module, a feature encoding module, and a bilinear pooling module. The image decomposition module is inspired by the Retinex theory and involves decoupling the input NTI into an illumination layer component responsible for illumination information and a reflection layer component responsible for content information. Then, the feature encoding module involves learning feature representations of degradations that are rooted in the two decoupled components separately. Finally, by modeling illumination-related and content-related degradations as two-factor variations, the two feature sets are bilinearly pooled together to form a unified representation for quality prediction. The superiority of the proposed DDB-Net has been well validated by extensive experiments on several benchmark datasets. The source code will be made available soon.