paper-with-me

홈 › Papers

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

2017-12-14 · Hongyu Ren, Diqi Chen, Yizhou Wang

Inspired by the free-energy brain theory, which implies that human visual system (HVS) tends to reduce uncertainty and restore perceptual details upon seeing a distorted image, we propose restorative adversarial net (RAN), a GAN-based model for no-reference image quality assessment (NR-IQA). RAN, which mimics the process of HVS, consists of three components: a restorator, a discriminator and an evaluator. The restorator restores and reconstructs input distorted image patches, while the discriminator distinguishes the reconstructed patches from the pristine distortion-free patches. After restoration, we observe that the perceptual distance between the restored and the distorted patches is monotonic with respect to the distortion level. We further define Gain of Restoration (GoR) based on this phenomenon. The evaluator predicts perceptual score by extracting feature representations from the distorted and restored patches to measure GoR. Eventually, the quality score of an input image is estimated by weighted sum of the patch scores. Experimental results on Waterloo Exploration, LIVE and TID2013 show the effectiveness and generalization ability of RAN compared to the state-of-the-art NR-IQA models.

📄 PDF Abstract BibTeX arXiv:1712.05444

Code (0)

등록된 구현이 없습니다.

Tasks

Image Quality AssessmentNo-Reference Image Quality AssessmentNR-IQAPerceptual Distance

Similar Papers 제목 키워드 기반

DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis

2022-04-21 · CVPR 2022 1 · Fatemeh Haghighi, Mohammad Reza Hosseinzadeh Taher, Michael B. Gotway, Jianming Liang

Discriminative learning, restorative learning, and adversarial learning have proven beneficial for self-supervised learning schemes in computer vision and medical imaging. Existing efforts, however, omit their synergisti…

Medical Image AnalysisRepresentation LearningSelf-Supervised Learning

Restorative Speech Enhancement: A Progressive Approach Using SE and Codec Modules

2024-10-02 · Hsin-Tien Chiang, Hao Zhang, Yong Xu, Meng Yu 외

In challenging environments with significant noise and reverberation, traditional speech enhancement (SE) methods often lead to over-suppressed speech, creating artifacts during listening and harming downstream tasks per…

QuantizationSpeech Enhancement

Step-Calibrated Diffusion for Biomedical Optical Image Restoration

2024-03-20 · Yiwei Lyu, Sung Jik Cha, Cheng Jiang, Asadur Chowdury 외

High-quality, high-resolution medical imaging is essential for clinical care. Raman-based biomedical optical imaging uses non-ionizing infrared radiation to evaluate human tissues in real time and is used for early cance…

DiagnosticImage GenerationImage Restoration

Mind the (optimality) Gap: A Gap-Aware Learning Rate Scheduler for Adversarial Nets

2023-01-31 · Hussein Hazimeh, Natalia Ponomareva

Adversarial nets have proved to be powerful in various domains including generative modeling (GANs), transfer learning, and fairness. However, successfully training adversarial nets using first-order methods remains a ma…

Domain AdaptationFairnessImage GenerationTransfer Learning

Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

2015-12-01 · NeurIPS 2015 12 · Emily L. Denton, Soumith Chintala, Arthur Szlam, Rob Fergus

In this paper we introduce a generative model capable of producing high quality samples of natural images. Our approach uses a cascade of convolutional networks (convnets) within a Laplacian pyramid framework to generate…