Search Results for author: Weixia Zhang

Found 18 papers, 14 papers with code

Assessing UHD Image Quality from Aesthetics, Distortions, and Saliency

1 code implementation1 Sep 2024 Wei Sun, Weixia Zhang, Yuqin Cao, Linhan Cao, Jun Jia, Zijian Chen, ZiCheng Zhang, Xiongkuo Min, Guangtao Zhai

To address this problem, we design a multi-branch deep neural network (DNN) to assess the quality of UHD images from three perspectives: global aesthetic characteristics, local technical distortions, and salient content perception.

4k Image Quality Assessment

Dual-Branch Network for Portrait Image Quality Assessment

1 code implementation14 May 2024 Wei Sun, Weixia Zhang, Yanwei Jiang, HaoNing Wu, ZiCheng Zhang, Jun Jia, Yingjie Zhou, Zhongpeng Ji, Xiongkuo Min, Weisi Lin, Guangtao Zhai

We employ the fidelity loss to train the model via a learning-to-rank manner to mitigate inconsistencies in quality scores in the portrait image quality assessment dataset PIQ.

Face Image Quality Assessment Image Quality Assessment +3

AIGIQA-20K: A Large Database for AI-Generated Image Quality Assessment

no code implementations4 Apr 2024 Chunyi Li, Tengchuan Kou, Yixuan Gao, Yuqin Cao, Wei Sun, ZiCheng Zhang, Yingjie Zhou, Zhichao Zhang, Weixia Zhang, HaoNing Wu, Xiaohong Liu, Xiongkuo Min, Guangtao Zhai

With the rapid advancements in AI-Generated Content (AIGC), AI-Generated Images (AIGIs) have been widely applied in entertainment, education, and social media.

Image Quality Assessment

When No-Reference Image Quality Models Meet MAP Estimation in Diffusion Latents

no code implementations11 Mar 2024 Weixia Zhang, Dingquan Li, Guangtao Zhai, Xiaokang Yang, Kede Ma

In this work, we show -- for the first time -- that NR-IQA models can be plugged into the maximum a posteriori (MAP) estimation framework for image enhancement.

Image Enhancement NR-IQA

Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective

1 code implementation CVPR 2023 Weixia Zhang, Guangtao Zhai, Ying WEI, Xiaokang Yang, Kede Ma

We aim at advancing blind image quality assessment (BIQA), which predicts the human perception of image quality without any reference information.

Scene Classification

Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop

1 code implementation3 Oct 2022 Weixia Zhang, Dingquan Li, Xiongkuo Min, Guangtao Zhai, Guodong Guo, Xiaokang Yang, Kede Ma

No-reference image quality assessment (NR-IQA) aims to quantify how humans perceive visual distortions of digital images without access to their undistorted references.

Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception

2 code implementations19 Aug 2021 Bowen Li, Weixia Zhang, Meng Tian, Guangtao Zhai, Xianpei Wang

The inaccessibility of reference videos with pristine quality and the complexity of authentic distortions pose great challenges for this kind of blind video quality assessment (BVQA) task.

Action Recognition Image Quality Assessment +3

Task-Specific Normalization for Continual Learning of Blind Image Quality Models

2 code implementations28 Jul 2021 Weixia Zhang, Kede Ma, Guangtao Zhai, Xiaokang Yang

In this paper, we present a simple yet effective continual learning method for blind image quality assessment (BIQA) with improved quality prediction accuracy, plasticity-stability trade-off, and task-order/-length robustness.

Continual Learning

Continual Learning for Blind Image Quality Assessment

1 code implementation19 Feb 2021 Weixia Zhang, Dingquan Li, Chao Ma, Guangtao Zhai, Xiaokang Yang, Kede Ma

In this paper, we formulate continual learning for BIQA, where a model learns continually from a stream of IQA datasets, building on what was learned from previously seen data.

Continual Learning

Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning

no code implementations22 Nov 2020 Weixia Zhang, Chao Ma, Qi Wu, Xiaokang Yang

We then propose to recursively alternate the learning schemes of imitation and exploration to narrow the discrepancy between training and inference.

Imitation Learning Navigate +1

Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild

1 code implementation28 May 2020 Weixia Zhang, Kede Ma, Guangtao Zhai, Xiaokang Yang

Nevertheless, due to the distributional shift between images simulated in the laboratory and captured in the wild, models trained on databases with synthetic distortions remain particularly weak at handling realistic distortions (and vice versa).

Learning-To-Rank

Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network

1 code implementation5 Jul 2019 Weixia Zhang, Kede Ma, Jia Yan, Dexiang Deng, Zhou Wang

We propose a deep bilinear model for blind image quality assessment (BIQA) that handles both synthetic and authentic distortions.

Image Classification

Learning to Blindly Assess Image Quality in the Laboratory and Wild

1 code implementation1 Jul 2019 Weixia Zhang, Kede Ma, Guangtao Zhai, Xiaokang Yang

Computational models for blind image quality assessment (BIQA) are typically trained in well-controlled laboratory environments with limited generalizability to realistically distorted images.

Learning-To-Rank

Cannot find the paper you are looking for? You can Submit a new open access paper.