Generation-Based Joint Luminance-Chrominance Learning for Underwater Image Quality Assessment

Wang, Zheyin; Shen, Liquan; Wang, Zhengyong; Lin, Yufei; Jin, Yanliang

doi:10.1109/tcsvt.2022.3212788

Cited by 19 publications

(1 citation statement)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FID [31] and DISTS [32] extract image features via a pre-trained classification network and then define some operations on them to capture the semantic and structural information. Recently, some efforts proposed objective metrics for several special visual scenes such as night-time images [34] and underwater images [35]. However, as demonstrated in Fig.…”

Section: Introductionmentioning

confidence: 99%

GAGCN: Generative adversarial graph convolutional network for non‐homogeneous texture extension synthesis

Xie

Qian

Nie

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

In the non‐homogeneous texture synthesis task, the overall visual characteristics should be consistent when extending the local patterns of the exemplar. The existing methods mainly focus on the local visual features of patterns but ignore the relative position features that are important for non‐homogeneous texture synthesis. Although these methods have achieved success on homogeneous textures, they cannot perform well on non‐homogeneous textures. Thus, it is desirable to model the dependence between pixels to improve the synthesis performance. To ensure synthesis results from both the local detail structure and the overall structure, this paper proposes a non‐homogeneous texture extended synthesis model (GAGCN) combining the generate adversarial network (GAN) and the graph convolutional network (GCN). The GAN learns the internal distribution of image patches, which makes the synthetic image have rich local details. The GCN learns the latent dependence between pixels according to the statistical characteristics of the image. Based on this, a novel graph similarity loss is proposed. This loss describes the latent spatial differences between the sample image and the generated image, which helps the model to better capture global features. Experiments show that our method outperforms existing methods on non‐homogeneous textures.

show abstract

Section: Introductionmentioning

confidence: 99%