RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment

Ren, H.; Chen, Diqi; Wang, Yizhou

doi:10.1609/aaai.v32i1.12258

Cited by 55 publications

(18 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To compensate for the lack of reference images, Ren et al [23] and Lin et al [24] use a generative adversarial network (GAN) to generate distortion-free images. The generated images and distorted ones are used to measure quality degradation caused by distortions.…”

Section: The Learning-based Biqa Methodsmentioning

confidence: 99%

“…Similar to refs. [1–39], we use two widely used metrics to measure the prediction accuracy of IQA models. One is the Pearson linear correlation coefficient (PLCC).…”

Section: Methodsmentioning

confidence: 99%

“…To compensate for the lack of reference images, Ren et al. [23] and Lin et al. [24] use a generative adversarial network (GAN) to generate distortion‐free images.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

CPDINet: Blind image quality assessment via a content perception and distortion inference network

Shao

Liu

Zhang

2022

IET Image Processing

View full text Add to dashboard Cite

Nowadays, it is still challenging for the blind image quality assessment (BIQA) to accurately predict quality scores of distorted images, since distorted images have rich content information and complex distortions. To solve these problems, a content perception and distortion inference network for BIQA is proposed, which divides IQA task into content perception and distortion inference processes. Since humans try to understand image content before perceiving quality scores, a content feature extractor is designed to explore content information in an image to deal with the content variation problem. To handle the distortion diversity problem, a distortion feature extractor is proposed to capture distortion features in images. Because extracted content features and distortion ones have different characteristics, attention-based fusion blocks to fuse multi-scale content features and distortion ones as guidance to selectively enhance important features based on calculated weight scores are proposed. With fused features, a quality prediction module is designed to regress multi-scale features to quality scores. Experiments are performed on six public IQA datasets, including LIVE, CSIQ, TID2013, LIVEC, KonIQ-10k, and SPAQ. Experimental results show that the proposed method can effectively predict quality scores for both synthetically and authentically distorted images than its peers, including the state-of-the-art methods.

show abstract

Section: The Learning-based Biqa Methodsmentioning

confidence: 99%

“…Similar to refs. [1–39], we use two widely used metrics to measure the prediction accuracy of IQA models. One is the Pearson linear correlation coefficient (PLCC).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

CPDINet: Blind image quality assessment via a content perception and distortion inference network

Shao

Liu

Zhang

2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…H-IQA improves the discriminator to recover high-quality pseudoreference images and then combines the distorted image and disparity map (the error between the distorted image and its pseudoreference image) to predict image quality. Considering the characteristics of HVS, Ren et al 27 . proposed a RAN4IQA model that consists of a generator, a discriminator, and an evaluator.…”

Section: Related Workmentioning

confidence: 99%

Three-stream network and improved attention mechanism-based blind image quality assessment

et al. 2023

View full text Add to dashboard Cite

.This paper proposes a network model based on a three-stream network and improved attention mechanism for blind image quality assessment (TSAIQA). The inputs of the three streams are the distorted image, the pseudoreference image obtained by the improved generative adversarial network (GAN), and the gradient map of the distorted image. The distorted image stream focuses on the holistic quality-related features, the pseudoreference image stream is used to supplement the lost features due to distortion, and the gradient stream explicitly extracts the quality-related structural features. In addition, spatial and channel attention mechanisms combining first- and second-order information are proposed, and the improved attention mechanisms are applied to the three-stream network to optimize spatial and channel-level features effectively. Finally, the three-stream fusion features are input to the quality regression network to predict the image quality. To demonstrate the effectiveness of the proposed model, experiments are conducted on four classical IQA databases and two new large-scale databases. The experimental results show that the results of our TSAIQA model outperform the most advanced IQA methods and confirm the effectiveness of the proposed network structure and attention mechanisms.

show abstract

“…Early works include support vector regression based methods Bovik 2010, 2011) and probability based methods (Mittal, Soundararajan, and Bovik 2012). With the prevalence of deep learning, massive of network architectures (Bosse et al 2016;Liu, Van De Weijer, and Bagdanov 2017;Talebi and Milanfar 2018;Lin and Wang 2018;Ren, Chen, and Wang 2018;Pan et al 2018;Lim, Kim, and Ra 2018;Zhang et al 2018bZhang et al , 2021 are proposed. Unfortunately, most of the existing IQA methods aim to assess the quality of natural images, while they are limited when dealing with generated images.…”

Section: Related Workmentioning

confidence: 99%

Assessing a Single Image in Reference-Guided Image Synthesis

Guo

Wang

et al. 2022

AAAI

View full text Add to dashboard Cite

Assessing the performance of Generative Adversarial Networks (GANs) has been an important topic due to its practical significance. Although several evaluation metrics have been proposed, they generally assess the quality of the whole generated image distribution. For Reference-guided Image Synthesis (RIS) tasks, i.e., rendering a source image in the style of another reference image, where assessing the quality of a single generated image is crucial, these metrics are not applicable. In this paper, we propose a general learning-based framework, Reference-guided Image Synthesis Assessment (RISA) to quantitatively evaluate the quality of a single generated image. Notably, the training of RISA does not require human annotations. In specific, the training data for RISA are acquired by the intermediate models from the training procedure in RIS, and weakly annotated by the number of models' iterations, based on the positive correlation between image quality and iterations. As this annotation is too coarse as a supervision signal, we introduce two techniques: 1) a pixel-wise interpolation scheme to refine the coarse labels, and 2) multiple binary classifiers to replace a naïve regressor. In addition, an unsupervised contrastive loss is introduced to effectively capture the style similarity between a generated image and its reference image. Empirical results on various datasets demonstrate that RISA is highly consistent with human preference and transfers well across models.

show abstract

RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment

Cited by 55 publications

References 23 publications

CPDINet: Blind image quality assessment via a content perception and distortion inference network

CPDINet: Blind image quality assessment via a content perception and distortion inference network

Three-stream network and improved attention mechanism-based blind image quality assessment

Assessing a Single Image in Reference-Guided Image Synthesis

Contact Info

Product

Resources

About