期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 31, 期 -, 页码 1613-1627出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2022.3144892
关键词
Image restoration; Visualization; Image quality; Task analysis; Feature extraction; Training; Distortion; No-reference image quality assessment; visual compensation restoration network; visual compensation module; optimized asymmetric residual block; error map loss; multi-level features
资金
- National Natural Science Foundation of China [61971232]
- Natural Science Foundation of Jiangsu Province of China [BK20201391]
- Natural Science Foundation of Tianjin [18ZXZNGX00110, 18JCJQJC45800]
This study proposed a no-reference image quality assessment method based on the visual compensation restoration network, which efficiently handles image restoration tasks with non-adversarial models, thereby improving the accuracy of image quality prediction.
Guided by the free-energy principle, generative adversarial networks (GAN)-based no-reference image quality assessment (NR-IQA) methods have improved the image quality prediction accuracy. However, the GAN cannot well handle the restoration task for the free-energy principle-guided NR-IQA methods, especially for the severely destroyed images, which results in that the quality reconstruction relationship between the distorted image and its restored image cannot be accurately built. To address this problem, a visual compensation restoration network (VCRNet)-based NR-IQA method is proposed, which uses a non-adversarial model to efficiently handle the distorted image restoration task. The proposed VCRNet consists of a visual restoration network and a quality estimation network. To accurately build the quality reconstruction relationship between the distorted image and its restored image, a visual compensation module, an optimized asymmetric residual block, and an error map-based mixed loss function, are proposed for increasing the restoration capability of the visual restoration network. For further addressing the NR-IQA problem of severely destroyed images, the multi-level restoration features which are obtained from the visual restoration network are used for the image quality estimation. To prove the effectiveness of the proposed VCRNet, seven representative IQA databases are used, and experimental results show that the proposed VCRNet achieves the state-of-the-art image quality prediction accuracy. The implementation of the proposed VCRNet has been released at https://github.com/NUIST-Videocoding/VCRNet.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据