Query：
学者姓名：陈光永
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
Retinex-based methods have become a general approach for solving low-light image enhancement (LLIE). However, traditional methods require post-processing of illumination (e.g., gamma correction), which lacks adaptability and disrupts the illumination structure. Retinex-based deep networks typically follow a 'decomposition-adjustment-exposure control' process, which is redundant and lacks robustness. One major issue is the inaccuracy in estimating and decomposing the initial illumination. Accurate initial illumination can prevent further post-processing instability. We propose IniRetinex, rethinking the Retinex-based LLIE method from the perspective of initialization. By using neural networks to provide reasonable initial illumination and solving for smooth illumination through optimization, higher performance LLIE is achieved. We construct a two-layer convolutional neural network to capture the low-frequency structure of the image, adaptively compensating for classical initial illumination and avoiding additional post-processing. The network requires no pre-training and can be implemented in an unsupervised manner with just a few iterations, making it highly efficient. Additionally, we propose a new illumination optimization strategy by introducing an additional proximal penalty term, improving illumination in areas with varying levels and enhancing image details. Extensive experiments on various low-light image datasets demonstrate that our method achieves state-of-the-art (SOTA) results on multiple benchmarks, offering higher stability and inference efficiency compared to current advanced methods.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Fan, Guodong , Yao, Zishu , Chen, Guang-Yong et al. IniRetinex: Rethinking Retinex-type Low-Light Image Enhancer via Initialization Perspective [J]. | THIRTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, AAAI-25, VOL 39 NO 3 , 2025 : 2834-2842 . |
| MLA | Fan, Guodong et al. "IniRetinex: Rethinking Retinex-type Low-Light Image Enhancer via Initialization Perspective" . | THIRTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, AAAI-25, VOL 39 NO 3 (2025) : 2834-2842 . |
| APA | Fan, Guodong , Yao, Zishu , Chen, Guang-Yong , Su, Jian-Nan , Gan, Min . IniRetinex: Rethinking Retinex-type Low-Light Image Enhancer via Initialization Perspective . | THIRTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, AAAI-25, VOL 39 NO 3 , 2025 , 2834-2842 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Retinex-based methods have become a general approach for solving low-light image enhancement (LLIE). However, traditional methods require post-processing of illumination (e.g., gamma correction), which lacks adaptability and disrupts the illumination structure. Retinex-based deep networks typically follow a ‘decomposition-adjustment-exposure control’ process, which is redundant and lacks robustness. One major issue is the inaccuracy in estimating and decomposing the initial illumination. Accurate initial illumination can prevent further post-processing instability. We propose IniRetinex, rethinking the Retinex-based LLIE method from the perspective of initialization. By using neural networks to provide reasonable initial illumination and solving for smooth illumination through optimization, higher performance LLIE is achieved. We construct a two-layer convolutional neural network to capture the low-frequency structure of the image, adaptively compensating for classical initial illumination and avoiding additional post-processing. The network requires no pre-training and can be implemented in an unsupervised manner with just a few iterations, making it highly efficient. Additionally, we propose a new illumination optimization strategy by introducing an additional proximal penalty term, improving illumination in areas with varying levels and enhancing image details. Extensive experiments on various low-light image datasets demonstrate that our method achieves state-of-the-art (SOTA) results on multiple benchmarks, offering higher stability and inference efficiency compared to current advanced methods. © 2025, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Keyword ：
Convolutional neural networks Convolutional neural networks Deep neural networks Deep neural networks Photointerpretation Photointerpretation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Fan, Guodong , Yao, Zishu , Chen, Guang-Yong et al. IniRetinex: Rethinking Retinex-type Low-Light Image Enhancer via Initialization Perspective [C] . 2025 : 2834-2842 . |
| MLA | Fan, Guodong et al. "IniRetinex: Rethinking Retinex-type Low-Light Image Enhancer via Initialization Perspective" . (2025) : 2834-2842 . |
| APA | Fan, Guodong , Yao, Zishu , Chen, Guang-Yong , Su, Jian-Nan , Gan, Min . IniRetinex: Rethinking Retinex-type Low-Light Image Enhancer via Initialization Perspective . (2025) : 2834-2842 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Remote sensing super-resolution (SR), which aims to reconstruct high-resolution (HR) images with rich spatial details from low-resolution (LR) remote sensing images predominantly composed of low-frequency components, presents a challenging yet practical task. Existing diffusion model (DM)-based methods for remote sensing SR are inefficient, requiring extensive iterations and often failing to recover high-frequency details adequately due to a lack of targeted processing for high-frequency components. To mitigate these challenges, this article introduces an efficient DM for remote sensing image SR, termed image reconstruction representation-diffusion model for super-resolution (IRR-DiffSR). IRR-DiffSR employs a feature extraction encoder to extract the image reconstruction representation (IRR) from ground-truth (GT) images, which makes the reconstruction network focus more on recovering high-frequency textures. Unlike traditional DM-based methods that learn the direct mapping from LR to HR images, IRR-DiffSR employs a pre-trained encoder to guide the DM in extracting consistent IRR directly from LR images. This auxiliary information aids in the efficient and effective reconstruction of high-frequency textures. By serving as an implicit reconstruction prior, this enables the DM to achieve accurate estimations with fewer iterations, thus assisting IRR-DiffSR in recovering high-frequency information more efficiently and effectively. Extensive experiments on four remote sensing datasets demonstrate that IRR-DiffSR achieves state-of-the-art reconstruction results in both real and synthetic scenarios. Specifically, in real scenarios, IRR-DiffSR outperforms the next best method by 0.766 and 0.69 in the naturalness image quality evaluator (NIQE), while in synthetic scenarios, it achieves peak signal-to-noise ratio (PSNR) improvements of 1.07 and 0.51. These results highlight the effectiveness and efficiency of IRR-DiffSR in recovering high-frequency details. Our code and pre-trained models have been uploaded to GitHub (https://github.com/55Dupup/IRR-DiffSR) for validation.
Keyword ：
Brain modeling Brain modeling Data mining Data mining Diffusion model (DM) Diffusion model (DM) Diffusion models Diffusion models Feature extraction Feature extraction image reconstruction image reconstruction Image reconstruction Image reconstruction Image restoration Image restoration image super-resolution (SR) image super-resolution (SR) reconstruction representation reconstruction representation remote sensing remote sensing Remote sensing Remote sensing Superresolution Superresolution Training Training Visualization Visualization
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Weng, Wu-Ding , Zheng, Chao-Wei , Su, Jian-Nan et al. Efficient High-Frequency Texture Recovery Diffusion Model for Remote Sensing Image Super-Resolution [J]. | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT , 2025 , 74 . |
| MLA | Weng, Wu-Ding et al. "Efficient High-Frequency Texture Recovery Diffusion Model for Remote Sensing Image Super-Resolution" . | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 74 (2025) . |
| APA | Weng, Wu-Ding , Zheng, Chao-Wei , Su, Jian-Nan , Chen, Guang-Yong , Gan, Min . Efficient High-Frequency Texture Recovery Diffusion Model for Remote Sensing Image Super-Resolution . | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT , 2025 , 74 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The identification of separable nonlinear models, prevalent in tasks such as signal analysis, image processing, time series analysis, and machine learning, presents a non-convex optimization challenge that necessitates the development of efficient identification algorithms. The Variable Projection (VP) algorithm has been proven to be quite effective for addressing these problems; however, traditional VP relying on the Hessian matrix and its inverse are highly time-consuming and unsuitable for complex, large-scale applications. This letter introduces a novel approach that employs the exponential moving average of gradient and gradient estimation bias to indirectly estimate the curvature of the objective landscape, proposing a Moving Average-based Variable Projection method (MAVP). The proposed algorithm utilizes only gradient information and can properly tackle the coupling relationships between different parameters during the optimization process, thereby achieving faster convergence. Numerical results on nonlinear time series analysis and image reconstruction demonstrate that the MAVP algorithm exhibits significant efficiency and effectiveness.
Keyword ：
Approximation algorithms Approximation algorithms Convergence Convergence Couplings Couplings Estimation Estimation Jacobian matrices Jacobian matrices Linear programming Linear programming Machine learning algorithms Machine learning algorithms Optimization Optimization Separable nonlinear optimization problem Separable nonlinear optimization problem Signal processing algorithms Signal processing algorithms system identification system identification variable projection variable projection Vectors Vectors
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xue, Peng , Gan, Min , Yuan, Fang et al. Moving Average-Based Variable Projection for Separable Nonlinear Problems [J]. | IEEE SIGNAL PROCESSING LETTERS , 2025 , 32 : 1900-1904 . |
| MLA | Xue, Peng et al. "Moving Average-Based Variable Projection for Separable Nonlinear Problems" . | IEEE SIGNAL PROCESSING LETTERS 32 (2025) : 1900-1904 . |
| APA | Xue, Peng , Gan, Min , Yuan, Fang , Chen, Guang-Yong , Chen, C. L. Philip . Moving Average-Based Variable Projection for Separable Nonlinear Problems . | IEEE SIGNAL PROCESSING LETTERS , 2025 , 32 , 1900-1904 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Reflection removal is a crucial issue in image reconstruction, especially for high-definition images. Removing undesirable reflections can greatly enhance the performance of various visual systems, such as medical imaging, autonomous driving, and security surveillance. However, the resolution of existing reflection removal datasets is not high and the training data heavily relies on synthetic data, which hampers the performance of reflection removal methods and restricts the development of effective techniques tailored for high-definition images. Therefore, this paper introduces a new dataset, Real-world Reflection Removal in 4K (RR4K). This novel dataset, with its large capacity and high resolution of 6000x 4000 pixels, represents a significant advancement in the field, ensuring a realistic and high quality benchmark. Furthermore, building upon the dataset, we propose an efficient method for single-image reflection removal, optimized for high-definition processing. This method employs the U-Net architecture, enhanced with large kernel distillation and scale-aware features, enabling it to effectively handle complex reflection scenarios while reducing computational demands. Comprehensive testing on the RR4K dataset and existing low-resolution datasets has demonstrated the method's superior efficiency and effectiveness. We believe that our constructed RR4K dataset can better evaluate and design algorithms for removing undesirable reflection from real-world high-definition images. Our dataset and code are available at https://github.com/jengchauwei/RR4K.
Keyword ：
benchmark dataset benchmark dataset Benchmark testing Benchmark testing Circuits and systems Circuits and systems Deep learning Deep learning Feature extraction Feature extraction Glass Glass image reconstruction image reconstruction Image reconstruction Image reconstruction Image resolution Image resolution Kernel Kernel Photography Photography Reflection Reflection Single-image reflection removal Single-image reflection removal
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Guang-Yong , Zheng, Chao-Wei , Fan, Guodong et al. Real-World Image Reflection Removal: An Ultra-High-Definition Dataset and an Efficient Baseline [J]. | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2025 , 35 (5) : 4397-4408 . |
| MLA | Chen, Guang-Yong et al. "Real-World Image Reflection Removal: An Ultra-High-Definition Dataset and an Efficient Baseline" . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 35 . 5 (2025) : 4397-4408 . |
| APA | Chen, Guang-Yong , Zheng, Chao-Wei , Fan, Guodong , Su, Jian-Nan , Gan, Min , Philip Chen, C. L. . Real-World Image Reflection Removal: An Ultra-High-Definition Dataset and an Efficient Baseline . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2025 , 35 (5) , 4397-4408 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Intracranial hemorrhage poses a critical threat to patient survival, necessitating rapid intervention to prevent devastating outcomes. Traditional segmentation methods in computer-aided diagnosis face significant challenges due to the inherent variability of hemorrhage regions. Recent advancements in segmentation, powered by foundation models and innovative utilization of prior knowledge, have shown promise; however, existing methods predominantly rely on point or bounding box prompts, which often fail to account for the intricate variability inherent in hemorrhage presentations. To tackle this challenge, we propose a knowledge- prompted segment anything model (KP-SAM) that integrates the specialized knowledge of neurologists into the segmentation process. By collaborating with expert neurologist, our method captures the nuanced characteristics of hemorrhage regions, effectively augmenting the limitations of using only points or bounding boxes. Furthermore, we developed a diagnostic support system for intracranial hemorrhage at the Affiliated Hospital of Qingdao University. Leveraging concise semantic information provided by radiologists, our system facilitates rapid and accurate diagnostic support for clinicians. Experimental results demonstrate that our method achieves state-of-the-art performance in real-world segmentation tasks and significantly enhances diagnostic accuracy for neurologists. This advancement not only enhances diagnostic precision but also highlights the transformative potential of integrating diverse data modalities in medical applications.
Keyword ：
CT CT Foundational models Foundational models Intracranial hemorrhage Intracranial hemorrhage Medical image segmentation Medical image segmentation Segment anything Segment anything
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Nie, Tianzong , Chen, Feiyan , Su, Jiannan et al. Knowledge-prompted intracranial hemorrhage segmentation on brain computed tomography [J]. | EXPERT SYSTEMS WITH APPLICATIONS , 2025 , 271 . |
| MLA | Nie, Tianzong et al. "Knowledge-prompted intracranial hemorrhage segmentation on brain computed tomography" . | EXPERT SYSTEMS WITH APPLICATIONS 271 (2025) . |
| APA | Nie, Tianzong , Chen, Feiyan , Su, Jiannan , Chen, Guangyong , Gan, Min . Knowledge-prompted intracranial hemorrhage segmentation on brain computed tomography . | EXPERT SYSTEMS WITH APPLICATIONS , 2025 , 271 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
We propose an online learning algorithm tailored for a class of machine learning models within a separable stochastic approximation framework. The central idea of our approach is to exploit the inherent separability in many models, recognizing that certain parameters are easier to optimize than others. This paper focuses on models where some parameters exhibit linear characteristics, which are common in machine learning applications. In our proposed algorithm, the linear parameters are updated using the recursive least squares (RLS) algorithm, akin to a stochastic Newton method. Subsequently, based on these updated linear parameters, the nonlinear parameters are adjusted using the stochastic gradient method (SGD). This dual-update mechanism can be viewed as a stochastic approximation variant of block coordinate gradient descent, where one subset of parameters is optimized using a second-order method while the other is handled with a first-order approach. We establish the global convergence of our online algorithm for non-convex cases in terms of the expected violation of first-order optimality conditions. Numerical experiments demonstrate that our method achieves significantly faster initial convergence and produces more robust performance compared to other popular learning algorithms. Additionally, our algorithm exhibits reduced sensitivity to learning rates and outperforms the recently proposed slimTrain algorithm (Newman et al. 2022). For validation, the code has been made available on GitHub.
Keyword ：
Approximation algorithms Approximation algorithms Artificial neural networks Artificial neural networks Convergence Convergence Convex functions Convex functions Machine learning Machine learning Machine learning algorithms Machine learning algorithms Minimization Minimization Online learning Online learning Optimization Optimization recursive least squares recursive least squares stochastic approximation stochastic approximation Stochastic processes Stochastic processes Training Training variable projection variable projection
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Gan, Min , Su, Xiang-xiang , Chen, Guang-yong et al. Online Learning Under a Separable Stochastic Approximation Framework [J]. | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 2025 , 47 (2) : 1317-1330 . |
| MLA | Gan, Min et al. "Online Learning Under a Separable Stochastic Approximation Framework" . | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 47 . 2 (2025) : 1317-1330 . |
| APA | Gan, Min , Su, Xiang-xiang , Chen, Guang-yong , Chen, Jing , Chen, C. L. Philip . Online Learning Under a Separable Stochastic Approximation Framework . | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 2025 , 47 (2) , 1317-1330 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
When capturing images under strong light sources at night, intense lens flare artifacts often appear, significantly degrading visual quality and impacting downstream computer vision tasks. Although transformer-based methods have achieved remarkable results in nighttime flare removal, they fail to adequately distinguish between flare and non-flare regions. This unified processing overlooks the unique characteristics of these regions, leading to suboptimal performance and unsatisfactory results in real-world scenarios. To address this critical issue, we propose a novel approach incorporating Location Prior Guidance (LPG) and a specialized flare removal model, LPFSformer. LPG is designed to accurately learn the location of flares within an image and effectively capture the associated glow effects. By employing Location Prior Injection (LPI), our method directs the model's focus towards flare regions through the interaction of frequency and spatial domains. Additionally, to enhance the recovery of high-frequency textures and capture finer local details, we designed a Global Hybrid Feature Compensator (GHFC). GHFC aggregates different expert structures, leveraging the diverse receptive fields and CNN operations of each expert to effectively utilize a broader range of features during the flare removal process. Extensive experiments demonstrate that our LPFSformer achieves state-of-the-art flare removal performance compared to existing methods. Our code and a pre-trained LPFSformer have been uploaded to GitHub for validation.
Keyword ：
deep learning deep learning Hardware Hardware Image reconstruction Image reconstruction Image restoration Image restoration Lenses Lenses Light sources Light sources low-level computer vision low-level computer vision Nighttime flare removal Nighttime flare removal Optical imaging Optical imaging Optical reflection Optical reflection Optical scattering Optical scattering Transformers Transformers Visualization Visualization
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Guang-Yong , Dong, Wei , Fan, Guodong et al. LPFSformer: Location Prior Guided Frequency and Spatial Interactive Learning for Nighttime Flare Removal [J]. | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2025 , 35 (4) : 3706-3718 . |
| MLA | Chen, Guang-Yong et al. "LPFSformer: Location Prior Guided Frequency and Spatial Interactive Learning for Nighttime Flare Removal" . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 35 . 4 (2025) : 3706-3718 . |
| APA | Chen, Guang-Yong , Dong, Wei , Fan, Guodong , Su, Jian-Nan , Gan, Min , Chen, C. L. Philip . LPFSformer: Location Prior Guided Frequency and Spatial Interactive Learning for Nighttime Flare Removal . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2025 , 35 (4) , 3706-3718 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
This paper delves into an in-depth exploration of the Variable Projection (VP) algorithm, a powerful tool for solving separable nonlinear optimization problems across multiple domains, including system identification, image processing, and machine learning. We first establish a theoretical framework to examine the effect of the approximate treatment of the coupling relationship among parameters on the local convergence of the VP algorithm and theoretically prove that the Kaufman's VP algorithm can achieve a similar convergence rate as the Golub & Pereyra's form. These studies fill the gap in the existing convergence theory analysis, and provide a solid foundation for understanding the mechanism of VP algorithm and broadening its application horizons. Furthermore, inspired by these theoretical insights, we design a refined VP algorithm, termed VPLR, to address separable nonlinear optimization problems with large residual. This algorithm enhances convergence performance by addressing the coupling relationship between parameters in separable models and continually refining the approximated Hessian matrix to counteract the influence of large residual. The effectiveness of this refined algorithm is corroborated through numerical experiments. (c) 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.
Keyword ：
Separable nonlinear optimization problem Separable nonlinear optimization problem System identification System identification Variable projection Variable projection
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Guangyong , Xue, Peng , Gan, Min et al. Variable Projection algorithms: Theoretical insights and a novel approach for problems with large residual [J]. | AUTOMATICA , 2025 , 177 . |
| MLA | Chen, Guangyong et al. "Variable Projection algorithms: Theoretical insights and a novel approach for problems with large residual" . | AUTOMATICA 177 (2025) . |
| APA | Chen, Guangyong , Xue, Peng , Gan, Min , Chen, Jing , Guo, Wenzhong , Chen, C. L. Philip . Variable Projection algorithms: Theoretical insights and a novel approach for problems with large residual . | AUTOMATICA , 2025 , 177 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Low-rank matrix decomposition with missing values is vital in computer vision and pattern recognition, yet it presents significant challenges. This problem can be viewed as a separable nonlinear optimization, but traditional methods often fail to account for the coupling between parameters and the impact of solution properties on visual reconstruction. We observe that such separable nonlinear problems frequently encounters narrow ravines filled with sharp minima. Classic alternating optimization methods, the Wiberg algorithm and its variants tend to linger in these regions, converging to sharp minima, thereby slowing convergence and degrading reconstruction quality. This promotes us to introduce the Adaptive Decoupled Variable Projection algorithm (ADVP), which can adaptively handle the coupling of parameters, significantly accelerate the convergence rate, and dynamically adjust the parameter search subspace, helping algorithms avoid these ravines towards flatter local minima. These flat minima exhibit robustness against missing data, noise, and outliers, enhancing the quality of visual reconstruction. Extensive experiments on synthetic and real datasets have validated the efficiency of ADVP and its superior performance in visual reconstruction.
Keyword ：
Low-rank matrix factorization Low-rank matrix factorization Separable nonlinear optimization problem Separable nonlinear optimization problem Variable projection Variable projection
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Gana, Min , Xue, Peng , Zhang, Fan et al. Adaptive decoupled strategy for robust and efficient low-rank matrix decomposition [J]. | NEUROCOMPUTING , 2025 , 649 . |
| MLA | Gana, Min et al. "Adaptive decoupled strategy for robust and efficient low-rank matrix decomposition" . | NEUROCOMPUTING 649 (2025) . |
| APA | Gana, Min , Xue, Peng , Zhang, Fan , Su, Xiang-Xiang , Lin, Xin , Chen, Guang-Yong . Adaptive decoupled strategy for robust and efficient low-rank matrix decomposition . | NEUROCOMPUTING , 2025 , 649 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
