Xu Zhang

Xu Zhang

Auto-generated profile, based on publicly available information

Xu Zhang

National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
9 May 2025 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
XZXu Zhang
Xu Zhang
JMJiaqi Ma
Jiaqi Ma
GWGuoli Wang
Guoli Wang
QZQian Zhang
Qian Zhang
HZHuan Zhang
Huan Zhang
LZLefei Zhang
Lefei Zhang
Existing All-in-One image restoration methods often fail to simultaneously perceive degradation types and severity levels, overlooking the importance of fine-grained quality perception. Moreover, these methods often utilize highly customized backbones, which hinder their adaptability and integration into more advanced restoration networks. To address these limitations, we propose Perceive-IR, a novel backbone-agnostic All-in-One image restoration framework designed for fine-grained quality control across various degradation types and severity levels. Its modular structure allows core components to function independently of specific backbones, enabling seamless integration into advanced restoration models without significant modifications. Specifically, Perceive-IR operates in two key stages: (1) multi-level quality-driven prompt learning stage, where a fine-grained quality perceiver is meticulously trained to discern threetier quality levels by optimizing the alignment between prompts and images within the CLIP perception space. This stage ensures a nuanced understanding of image quality, laying the groundwork for subsequent restoration; (2) restoration stage, where the quality perceiver is seamlessly integrated with a difficulty-adaptive perceptual loss, forming a quality-aware learning strategy. This strategy not only dynamically differentiates sample learning difficulty but also achieves fine-grained quality control by driving the restored image toward the ground truth while simultaneously pulling it away from both low- and medium-quality samples. Furthermore, Perceive-IR incorporates a Semantic Guidance Module (SGM) and Compact Feature Extraction (CFE). The SGM leverages semantic information from pre-trained vision models to provide high-level contextual guidance, while the CFE focuses on extracting degradation-specific features, ensuring accurate handling of diverse image degradations. Extensive experiments demonstrate that Perceive-IR not only surpasses state-of-the-art methods but also generalizes reliably to zero-shot realworld and unknown degraded scenes, while adapting seamlessly to different backbone networks. This versatility underscores the framework’s robustness and backbone-agnostic design.

14 October 2025 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
XZXu Zhang
Xu Zhang
HZHuan Zhang
Huan Zhang
GWGuoli Wang
Guoli Wang
QZQian Zhang
Qian Zhang
LZLefei Zhang
Lefei Zhang
BDBo Du
Bo Du
Existing underwater image restoration (UIR) methods generally only handle color distortion or jointly address color and haze issues, but they often overlook the more complex degradations that can occur in underwater scenes. To address this limitation, we propose a Universal Underwater Image Restoration method, termed as UniUIR, considering the complex scenario of real-world underwater mixed distortions as an all-in-one manner. To disentangle degradation-specific effects and capture their inter-correlations, we propose the Mamba Mixture-of-Experts module (MMoEM). Each expert specializes in distinct aspects of degradation, while gating mechanism dynamically routes features to appropriate experts. This design enables collaborative prior extraction and preserves global context, all within linear computational complexity. Building upon this foundation, to enhance degradation representation and address the task conflicts that arise when handling multiple types of degradation, we introduce the spatial-frequency prior generator. This module extracts degradation prior information in both spatial and frequency domains, and adaptively selects the most appropriate task-specific prompts based on image content, thereby improving the accuracy of image restoration. Finally, to more effectively address complex, region-dependent distortions in UIR task, we incorporate depth information derived from a large-scale pre-trained depth prediction model, thereby enabling the network to perceive and leverage depth variations across different image regions to handle localized degradation. Extensive experiments demonstrate that UniUIR can produce more attractive results across qualitative and quantitative comparisons, and shows strong generalization than state-of-the-art methods.

3 February 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
XZXu Zhang
Xu Zhang
NCNian Cai
Nian Cai
HZHuan Zhang
Huan Zhang
Yun ZhangYun Zhang
Yun Zhang
JDJianglei Di
Jianglei Di
WLWeisi Lin
Weisi Lin
Recently, CNN-based post-processing has shown great potential in Synthesized View Quality Enhancement (SVQE). However, due to the limited receptive field of convolution, it is ineffective in explicitly modeling long-range dependencies, which are critical to eliminate the distortion induced by Depth Image Based Rendering (DIBR) in synthesized views. Although transformers exhibit tremendous success at learning global contextual information, it is weak at extracting local texture information. To take full advantages of the CNN and transformer, we present a novel U-shaped hybrid transformer with asymmetric flow division to collaboratively capture global-local information for SVQE, termed as AFD-former. Specifically, the AFD-former utilizes the Transformer-CNN Block (TCB) as encoder and decoder, in which several Dynamic Hybrid Attention Blocks (DHABs) are designed to simultaneously model long-range interactions and retain texture details. Then, considering that the deeper layers of the U-shaped network play more roles in capturing global information while shallow layers more in extracting local information, an Asymmetric Flow Division Unit (AFDU) is embedded into each DHAB to assign different contributions of global-local contextual information to the transformer and CNN branches across different layers. Finally, a dynamic learnable modulator is incorporated into two branches to help model effectively feature representation learning. That can be viewed as the dynamic process of adjusting the weight for each channel of the input feature based on contextual cues. Extensive experiments demonstrate that the proposed AFD-former can significantly enhance perceptual quality of synthesized views with similar SVQE speed compared with the related state-of-the-art SVQE methods. The source code will be available at https://github.com/House-yuyu/AFD-former.

8 September 2025 in Computer Vision and Image Understanding
Verified
Journal Article
Closed access
HZHuan Zhang
Huan Zhang
XZXu Zhang
Xu Zhang
NCNian Cai
Nian Cai
JDJianglei Di
Jianglei Di
Yun ZhangYun Zhang
Yun Zhang

23 November 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
HZHuan Zhang
Huan Zhang
XZXu Zhang
Xu Zhang
LZLinwei Zhu
Linwei Zhu
Yun ZhangYun Zhang
Yun Zhang
JCJiangzhong Cao
Jiangzhong Cao
Wing-Kuen LingWing-Kuen Ling
Wing-Kuen Ling

23 December 2022
Verified
Conference Paper
Open access
DZDongsheng Zheng
Dongsheng Zheng
HZHuan Zhang
Huan Zhang
JCJiangzhong Cao
Jiangzhong Cao
XZXu Zhang
Xu Zhang
XYXimei Yao
Ximei Yao
Wing-Kuen LingWing-Kuen Ling
Wing-Kuen Ling
Depth-Image-Based Rendering (DIBR) technology is widely used in 3D video systems to synthesize virtual views. However, the DIBR rendering process tends to introduce local and global distortions, especially local geometric distortion, that will severely affect the perception. In addition, traditional 2D quality metrics may fail to handle this issue since only global distortion is considered. Therefore, in order to evaluate the quality of virtual views more accurately, we propose a full reference DIBR-synthesized views quality assessment model that considers both local and global aspects. Local standard deviation texture images of the reference and distorted images are used to detect local distortions due to local distortions in the virtual view result in a large degree of variation in texture information. The intensity similarity and gradient similarity of the texture images are fused to obtain the final local distortion map. The perceptual hash similarity between the reference and the distorted image is used to quantify the global sharpness due to its powerful frequency domain analysis capability. Depending on the experimental results on the IRCCyN/IVC and IETR databases, the performance of our metric is competitive with the state-of-the-art methods.