中文
相关论文

相关论文: DR.Experts: Differential Refinement of Distortion-…

200 篇论文

Blind image quality assessment (IQA) in the wild, which assesses the quality of images with complex authentic distortions and no reference images, presents significant challenges. Given the difficulty in collecting large-scale training…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Honghao Fu , Yufei Wang , Wenhan Yang , Alex C. Kot , Bihan Wen

The 4K content can deliver a more immersive visual experience to consumers due to the huge improvement of spatial resolution. However, existing blind image quality assessment (BIQA) methods are not suitable for the original and upscaled 4K…

多媒体 · 计算机科学 2022-06-10 Wei Lu , Wei Sun , Xiongkuo Min , Wenhan Zhu , Quan Zhou , Jun He , Qiyuan Wang , Zicheng Zhang , Tao Wang , Guangtao Zhai

Objective assessment of image quality is fundamentally important in many image processing tasks. In this work, we focus on learning blind image quality assessment (BIQA) models which predict the quality of a digital image with no access to…

计算机视觉与模式识别 · 计算机科学 2019-04-16 Kede Ma , Wentao Liu , Tongliang Liu , Zhou Wang , Dacheng Tao

A key problem in blind image quality assessment (BIQA) is how to effectively model the properties of human visual system in a data-driven manner. In this paper, we propose a simple and efficient BIQA model based on a novel framework which…

计算机视觉与模式识别 · 计算机科学 2019-03-12 Da Pan , Ping Shi , Ming Hou , Zefeng Ying , Sizhe Fu , Yuan Zhang

The optimization objective of regression-based blind image quality assessment (IQA) models is to minimize the mean prediction error across the training dataset, which can lead to biased parameter estimation due to potential training data…

计算机视觉与模式识别 · 计算机科学 2023-10-24 Xiaoqi Wang , Jian Xiong , Hao Gao , Weisi Lin

Opinion-Unaware Blind Image Quality Assessment (OU-BIQA) models aim to predict image quality without training on reference images and subjective quality scores. Thereinto, image statistical comparison is a classic paradigm, while the…

计算机视觉与模式识别 · 计算机科学 2024-01-17 Yixuan Li , Peilin Chen , Hanwei Zhu , Keyan Ding , Leida Li , Shiqi Wang

Blind image quality assessment (BIQA) remains challenging due to the diversity of distortion and image content variation, which complicate the distortion patterns crossing different scales and aggravate the difficulty of the regression…

图像与视频处理 · 电气工程与系统科学 2023-11-06 Qingyi Pan , Ning Guo , Letu Qingge , Jingyi Zhang , Pei Yang

Image quality assessment (IQA) is very important for both end-users and service providers since a high-quality image can significantly improve the user's quality of experience (QoE) and also benefit lots of computer vision algorithms. Most…

多媒体 · 计算机科学 2023-04-28 Wei Sun , Xiongkuo Min , Danyang Tu , Guangtao Zhai , Siwei Ma

Deep learning-based methods have significantly influenced the blind image quality assessment (BIQA) field, however, these methods often require training using large amounts of human rating data. In contrast, traditional knowledge-based…

计算机视觉与模式识别 · 计算机科学 2024-05-30 Zhangkai Ni , Yue Liu , Keyan Ding , Wenhan Yang , Hanli Wang , Shiqi Wang

Blind Image Quality Assessment (BIQA) is a fundamental task in computer vision, which however remains unresolved due to the complex distortion conditions and diversified image contents. To confront this challenge, we in this paper propose a…

计算机视觉与模式识别 · 计算机科学 2023-04-12 Guanyi Qin , Runze Hu , Yutao Liu , Xiawu Zheng , Haotian Liu , Xiu Li , Yan Zhang

Blind image quality assessment (BIQA) is a challenging problem with important real-world applications. Recent efforts attempting to exploit powerful representations by deep neural networks (DNN) are hindered by the lack of subjectively…

计算机视觉与模式识别 · 计算机科学 2023-05-25 Zehong Zhou , Fei Zhou , Guoping Qiu

Existing blind image quality assessment (BIQA) methods focus on designing complicated networks based on convolutional neural networks (CNNs) or transformer. In addition, some BIQA methods enhance the performance of the model in a two-stage…

计算机视觉与模式识别 · 计算机科学 2024-02-20 Qunyue Huang , Bin Fang

Blind video quality assessment (BVQA) is a highly challenging task due to the intrinsic complexity of video content and visual distortions, especially given the high popularity of social media videos, which originate from a wide range of…

图像与视频处理 · 电气工程与系统科学 2026-01-06 Wei Sun , Linhan Cao , Jun Jia , Zhichao Zhang , Zicheng Zhang , Xiongkuo Min , Guangtao Zhai

Image quality assessment (IQA) has long been a fundamental challenge in image understanding. In recent years, deep learning-based IQA methods have shown promising performance. However, the lack of large amounts of labeled data in the IQA…

计算机视觉与模式识别 · 计算机科学 2024-07-08 Jinsong Shi , Pan Gao , Xiaojiang Peng , Jie Qin

Blind image quality assessment (BIQA) remains a very challenging problem due to the unavailability of a reference image. Deep learning based BIQA methods have been attracting increasing attention in recent years, yet it remains a difficult…

计算机视觉与模式识别 · 计算机科学 2017-12-06 Hui Zeng , Lei Zhang , Alan C. Bovik

Blind image quality assessment (BIQA) aims at automatically and accurately forecasting objective scores for visual signals, which has been widely used to monitor product and service quality in low-light applications, covering smartphone…

计算机视觉与模式识别 · 计算机科学 2023-10-10 Miaohui Wang , Zhuowei Xu , Mai Xu , Weisi Lin

Video Quality Assessment (VQA) aims to evaluate video quality based on perceptual distortions and human preferences. Despite the promising performance of existing methods using Convolutional Neural Networks (CNNs) and Vision Transformers…

计算机视觉与模式识别 · 计算机科学 2025-05-07 Wei-Ting Chen , Yu-Jiet Vong , Yi-Tsung Lee , Sy-Yen Kuo , Qiang Gao , Sizhuo Ma , Jian Wang

Image Quality Assessment algorithms predict a quality score for a pristine or distorted input image, such that it correlates with human opinion. Traditional methods required a non-distorted "reference" version of the input image to compare…

图像与视频处理 · 电气工程与系统科学 2020-07-21 Subhayan Mukherjee , Giuseppe Valenzise , Irene Cheng

We study deep neural networks for classification of images with quality distortions. We first show that networks fine-tuned on distorted data greatly outperform the original networks when tested on distorted data. However, fine-tuned…

计算机视觉与模式识别 · 计算机科学 2017-03-24 Samuel Dodge , Lina Karam

Recent advances in Image Quality Assessment (IQA) have leveraged Multi-modal Large Language Models (MLLMs) to generate descriptive explanations. However, despite their strong visual perception modules, these models often fail to reliably…

计算机视觉与模式识别 · 计算机科学 2025-12-11 Yuan Li , Zitang Sun , Yen-Ju Chen , Shin'ya Nishida