Rui Zhou

Rui Zhou

Auto-generated profile, based on publicly available information

Rui Zhou

Faculty of Information Science and Engineering, Ningbo University, Ningbo, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 August 2024 in IEEE Transactions on Broadcasting
Verified
Journal Article
Closed access
RZRui Zhou
Rui Zhou
GJGangyi Jiang
Gangyi Jiang
YCYueli Cui
Yueli Cui
YCYeyao Chen
Yeyao Chen
HXHaiyong Xu
Haiyong Xu
MYMei Yu
Mei Yu
Light field imaging captures both the intensity and directional information of light rays, providing users with more immersive visual experience. However, during the processes of imaging, processing, coding and reconstruction, light field images (LFIs) may encounter various distortions that degrade their visual quality. Compared to two-dimensional image quality assessment, light field image quality assessment (LFIQA) needs to consider not only the image quality in the spatial domain but also the quality degradation in the angular domain. To effectively model the factors related to visual perception and LFI quality, this paper proposes a multi-scale attention feature fusion based blind LFIQA metric, named MAFBLiF. The proposed metric consists of the following parts: MLI-Patch generation, spatial-angular feature separation module, spatial-angular feature extraction backbone network, pyramid feature alignment module and patch attention module. These modules are specifically designed to extract spatial and angular information of LFIs, and capture multi-level information and regions of interest. Furthermore, a pooling scheme guided by the LFI’s gradient information and saliency is proposed, which integrates the quality of all MLI-patches into the overall quality of the input LFI. Finally, to demonstrate the effectiveness of the proposed metric, extensive experiments are conducted on three representative LFI quality evaluation datasets. The experimental results show that the proposed metric outperforms other state-of-the-art image quality assessment metrics. The code will be publicly available at https://github.com/oldblackfish/MAFBLiF.

17 January 2025 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
RZRui Zhou
Rui Zhou
GJGangyi Jiang
Gangyi Jiang
LZLinwei Zhu
Linwei Zhu
YCYueli Cui
Yueli Cui
TLTing Luo
Ting Luo
Due to the distortions occurring at various stages from acquisition to visualization, light field image quality assessment (LFIQA) is crucial for guiding the processing of light field images (LFIs). In this letter, we propose a new blind LFIQA metric via frequency domain analysis and auxiliary learning, termed as FABLFQA. First, spatial-angular patches are extracted from LFIs and further processed through discrete cosine transform to obtain light field frequency maps. Subsequently, a concise and efficient frequency-aware deep learning network is designed to extract frequency features, including the frequency descriptor, 3D ConvBlock, and frequency transformer. Finally, a distortion type discrimination auxiliary task is employed to facilitate the learning of the main quality assessment task. Experimental results on three representative LFI datasets show that the proposed metric outperforms the state-of-the-art metrics. The code of the proposed metric will be publicly available athttps://github.com/oldblackfish/FABLFQA.

26 January 2026 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
RZRui Zhou
Rui Zhou
GJGangyi Jiang
Gangyi Jiang
YCYeyao Chen
Yeyao Chen
YCYueli Cui
Yueli Cui
TLTing Luo
Ting Luo
HXHaiyong Xu
Haiyong Xu
Light Field Images (LFIs) capture both angular and spatial information, providing a richer representation of scenes. However, due to the limitations of commercial light field camera hardware, the captured field of view is relatively narrow. To address this, image stitching techniques are commonly employed to extend the field of view, resulting in Wide field of view Light Field Images (WLFIs). Given the massive data volume of WLFIs, various visual compression distortions are easily introduced during compression, posing new challenges for measuring the quality of distorted WLFIs. To tackle this issue, this paper first conducts a subjective experiment to measure the quality of distorted WLFIs and constructs a new benchmark quality measurement database, which includes corresponding subjective quality scores. Specifically, each WLFI in the database is generated by stitching 13 LFIs captured by a light field camera, with the focus on distortions introduced by mainstream light field image compression techniques. Furthermore, a novel objective blind metric based on epipolar plane pseudo video sequence representation is proposed to measure the visual quality degradation of WLFIs. Finally, comprehensive experiments are conducted on the proposed database, comparing the proposed metric with several state-of-the-art light field image quality assessment metrics. Experimental results demonstrate that the proposed metric outperforms most existing metrics in various aspects. The proposed database and metric will be publicly released at https://github.com/oldblackfish/NBU-WLFI.

19 December 2025 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
YSYu Sun
Yu Sun
RZRui Zhou
Rui Zhou
YCYueli Cui
Yueli Cui
MJMing Jin
Ming Jin
GJGangyi Jiang
Gangyi Jiang
The limited field of view (FoV) of commercial light field cameras has driven development of various stitching techniques to generate wide-FoV light field images (WLFIs). However, these techniques often introduce local distortions and angular inconsistencies, posing significant challenges for WLFI quality assessment. In this letter, a no-reference WLFI quality assessment (WLFIQA) method based on structured representation and progressive learning is proposed. Specifically, considering the high-dimensional characteristics and distortion properties of WLFIs, a novel joint spatial-angular representation strategy is first designed. For the angular domain, horizontal and vertical sub-aperture images stacks are employed to characterize angular features; for the spatial domain each sub-aperture image is divided into four quadrants, and image blocks containing complementary cues from corresponding positions across different quadrants are used as input for subsequent feature extraction. Furthermore, a global-local feature extraction network is employed to further model multi-scale distortion characteristics. Finally, a progressive learning strategy is designed to enhance the performance of overall perceptual evaluation. Experimental results on a benchmark WLFI dataset show that the proposed method outperforms existing quality methods. The code will be available at https://github.com/sunyu-iy/WLFIQA.