Adaptive Hypergraph Convolutional Network for No-Reference 360-degree Image Quality Assessment

2021-05-19 · Jun Fu, Chen Hou, Wei Zhou, Jiahua Xu, Zhibo Chen

In no-reference 360-degree image quality assessment (NR 360IQA), graph convolutional networks (GCNs), which model interactions between viewports through graphs, have achieved impressive performance. However, prevailing GCN-based NR 360IQA methods suffer from three main limitations. First, they only use high-level features of the distorted image to regress the quality score, while the human visual system (HVS) scores the image based on hierarchical features. Second, they simplify complex high-order interactions between viewports in a pairwise fashion through graphs. Third, in the graph construction, they only consider spatial locations of viewports, ignoring its content characteristics. Accordingly, to address these issues, we propose an adaptive hypergraph convolutional network for NR 360IQA, denoted as AHGCN. Specifically, we first design a multi-level viewport descriptor for extracting hierarchical representations from viewports. Then, we model interactions between viewports through hypergraphs, where each hyperedge connects two or more viewports. In the hypergraph construction, we build a location-based hyperedge and a content-based hyperedge for each viewport. Experimental results on two public 360IQA databases demonstrate that our proposed approach has a clear advantage over state-of-the-art full-reference and no-reference IQA models.

📄 PDF Abstract BibTeX arXiv:2105.09143

Code (0)

등록된 구현이 없습니다.

Tasks

graph constructionImage Quality Assessment

Methods 이 논문이 사용한 방법론

Graph Convolutional Networks 설명 없음

Learning Low Degree Hypergraphs

2022-02-21 · Eric Balkanski, Oussama Hanguir, Shatian Wang

We study the problem of learning a hypergraph via edge detecting queries. In this problem, a learner queries subsets of vertices of a hidden hypergraph and observes whether these subsets contain an edge or not. In genera…

Convolutional Signal Propagation: A Simple Scalable Algorithm for Hypergraphs

2024-09-26 · Pavel Procházka, Marek Dědič, Lukáš Bajer

Last decade has seen the emergence of numerous methods for learning on graphs, particularly Graph Neural Networks (GNNs). These methods, however, are often not directly applicable to more complex structures like bipartit…

Node Classification Retrieval

Inhomogeneous Social Recommendation with Hypergraph Convolutional Networks

2021-11-05 · Zirui Zhu, Chen Gao, Xu Chen, Nian Li 외

Incorporating social relations into the recommendation system, i.e. social recommendation, has been widely studied in academic and industrial communities. While many promising results have been achieved, existing methods…

Triplet

DyHCN: Dynamic Hypergraph Convolutional Networks

2021-01-01 · Nan Yin, Zhigang Luo, Wenjie Wang, Fuli Feng 외

Hypergraph Convolutional Network (HCN) has become a default choice for capturing high-order relations among nodes, \emph{i.e., } encoding the structure of a hypergraph. However, existing HCN models ignore the dynamic evo…

Learnable Hypergraph Laplacian for Hypergraph Learning

2021-06-12 · Jiying Zhang, Yuzhao Chen, Xi Xiao, Runiu Lu 외

Hypergraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph-structured data. However, most existing convolution filters are localized and determ…

Graph Classification Node Classification