Xu Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xu Zhang has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Huan Zhang
School of Information Engineering, Guangdong University of Technology, Guangzhou, China
7 shared publications - Lefei Zhang
School of Computer Science, Wuhan University, Wuhan, China
3 shared publications - Yun Zhang
School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China
3 shared publications - Bingo Wing-Kuen Ling
Faculty of Information Engineering, Guangdong University of Technology, Guangzhou, China
2 shared publications - Guoli Wang
Horizon Robotics, Beijing, China
2 shared publications Jianglei Di
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3239-3248
ClusIR: Towards Cluster-Guided All-in-One Image Restoration
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3239-3248
Open AccessClusIR: Towards Cluster-Guided All-in-One Image Restoration
- Open Access
- 8 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (6) , 1-19
Enhanced Quality-Aware Scalable Underwater Image Compression
Underwater imaging plays a pivotal role in marine exploration and ecological monitoring. However, it faces significant challenges of limited transmission bandwidth and severe distortion in the aquatic environment. In this work, to achieve the target of both underwater image compression and enhancement simultaneously, an enhanced quality-aware scalable underwater image compression framework is presented, which comprises a Base Layer (BL) and an Enhancement Layer (EL). In the BL, the underwater image is represented by a controllable number of non-zero sparse coefficients for coding bits saving. Furthermore, the underwater image enhancement dictionary is derived with shared sparse coefficients to make reconstruction close to the enhanced version. In the EL, a dual-branch filter comprising rough filtering and detail refinement branches is designed to produce a pseudo-enhanced version for residual redundancy removal and to improve the quality of final reconstruction. Extensive experimental results demonstrate that the proposed scheme outperforms the state-of-the-art works under five large-scale underwater image datasets in terms of Underwater Image Quality Measure (UIQM).
- 8 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (6) , 1-19
Open AccessEnhanced Quality-Aware Scalable Underwater Image Compression
Underwater imaging plays a pivotal role in marine exploration and ecological monitoring. However, it faces significant challenges of limited transmission bandwidth and severe distortion in the aquatic environment. In this work, to achieve the target of both underwater image compression and enhancement simultaneously, an enhanced quality-aware scalable underwater image compression framework is presented, which comprises a Base Layer (BL) and an Enhancement Layer (EL). In the BL, the underwater image is represented by a controllable number of non-zero sparse coefficients for coding bits saving. Furthermore, the underwater image enhancement dictionary is derived with shared sparse coefficients to make reconstruction close to the enhanced version. In the EL, a dual-branch filter comprising rough filtering and detail refinement branches is designed to produce a pseudo-enhanced version for residual redundancy removal and to improve the quality of final reconstruction. Extensive experimental results demonstrate that the proposed scheme outperforms the state-of-the-art works under five large-scale underwater image datasets in terms of Underwater Image Quality Measure (UIQM).
- Top Cited Papers
- 14 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 6963-6977
UniUIR: Considering Underwater Image Restoration as an All-in-One Learner
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.
- 14 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 6963-6977
Top Cited PapersUniUIR: Considering Underwater Image Restoration as an All-in-One Learner
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.
- 8 September 2025
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 261
Joint multi-dimensional dynamic attention and transformer for general image restoration
- 8 September 2025
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 261
Joint multi-dimensional dynamic attention and transformer for general image restoration
- Top Cited Papers
- 9 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 2018-2033
Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration
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.
- 9 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 2018-2033
Top Cited PapersPerceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration
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.
- 3 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (8) , 3786-3798
AFD-Former: A Hybrid Transformer With Asymmetric Flow Division for Synthesized View Quality Enhancement
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.
- 3 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 33 (8) , 3786-3798
AFD-Former: A Hybrid Transformer With Asymmetric Flow Division for Synthesized View Quality Enhancement
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.
- Open Access
- 23 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Evaluating Quality of DIBR-synthesized Views based on Texture and Perceptual Hashing Similarity
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.
- 23 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessEvaluating Quality of DIBR-synthesized Views based on Texture and Perceptual Hashing Similarity
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.
- 14 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 963-967
A fast algorithm for underwater image restoration based on CUDA
Due to the severe underwater environment condition and the effects of water scattering, the images acquired by underwater optical vision system often have many problems such as low resolution, contrast and serious color shifts. Many scholars have proposed many image restoration algorithms and proved to be effective, but there is still a problem of excessive time consumption. In this regard, this article comprehensively considers the principle of dark channel underwater image imaging, combined with parallel computing related theories, and modified the serial model of the traditional underwater image restoration algorithm to be suitable for CUDA (Compute Unified Device Architecture) Parallel model. Through experimental tests, while ensuring a restoration effect similar to similar algorithms, a speed increase of about 14 times has been achieved, and the real-time restoration of underwater images is realized.
- 14 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 963-967
A fast algorithm for underwater image restoration based on CUDA
Due to the severe underwater environment condition and the effects of water scattering, the images acquired by underwater optical vision system often have many problems such as low resolution, contrast and serious color shifts. Many scholars have proposed many image restoration algorithms and proved to be effective, but there is still a problem of excessive time consumption. In this regard, this article comprehensively considers the principle of dark channel underwater image imaging, combined with parallel computing related theories, and modified the serial model of the traditional underwater image restoration algorithm to be suitable for CUDA (Compute Unified Device Architecture) Parallel model. Through experimental tests, while ensuring a restoration effect similar to similar algorithms, a speed increase of about 14 times has been achieved, and the real-time restoration of underwater images is realized.