Xinggui Xu
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
Xinggui Xu has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
Hao Xian
Key Laboratory on Adaptive Optics and Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China
2 shared publicationsHong Li
School of Information Yunnan University of Finance and Economics 650221 Kunming China
2 shared publicationsPing Yang
Key Laboratory on Adaptive Optics and Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, China
2 shared publicationsYong Liu
School of Optoelectronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
2 shared publicationsBin Chai
School of Information Yunnan University of Finance and Economics 650221 Kunming China
1 shared publication- Bing Xu
Key Laboratory on Adaptive Optics, Chinese Academy of Sciences, Chengdu 610209, China
1 shared publication
Latest Publications
- 19 July 2026
- Published by Springer Nature
- p. 103-114
Taming Depth Priors for Robust and High-Quality Low-Light Image Enhancement
- 19 July 2026
- Published by Springer Nature
- p. 103-114
Taming Depth Priors for Robust and High-Quality Low-Light Image Enhancement
- Open Access
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 291-298
A Data-Driven Model of Social Connectedness and Hidden Absenteeism Among Medical Students from Minority Regions
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 291-298
Open AccessA Data-Driven Model of Social Connectedness and Hidden Absenteeism Among Medical Students from Minority Regions
- Open Access
- 28 September 2023
- Published by Atlantis Press SARL
- p. 741-746
Influence of Empathy Fatigue on Medical Students' Implicit Absenteeism in Ethnic Minority Areas
- 28 September 2023
- Published by Atlantis Press SARL
- p. 741-746
Open AccessInfluence of Empathy Fatigue on Medical Students' Implicit Absenteeism in Ethnic Minority Areas
- Open Access
Adaptive Reversible 3D Model Hiding Method Based on Convolutional Neural Network Prediction Error Expansion
Although reversible data hiding technology is widely used, it still faces several challenges and issues. These include ensuring the security and reliability of embedded secret data, improving the embedding capacity, and maintaining the quality of media data. Additionally, irregular data types, such as three-dimensional point clouds and triangle mesh-represented 3D models, lack an ordered structure in their representation. As a result, embedding these irregular data into digital media does not provide sufficient information for the complete recovery of the original data during extraction. To address this issue, this paper proposes a method based on convolutional neural network prediction error expansion to enhance the embedding capacity of carrier images while maintaining acceptable visual quality. The triangle mesh representation of the 3D model is regularized in a two-dimensional parameterization domain, and the regularized 3D model is reversibly embedded into the image. The process of embedding and extracting confidential information in carrier images is symmetrical, and the regularization and restoration of 3D models are also symmetrical. Experiments show that the proposed method increases the reversible embedding capacity, and the triangle mesh can be conveniently subjected to reversible hiding.
Open AccessAdaptive Reversible 3D Model Hiding Method Based on Convolutional Neural Network Prediction Error Expansion
Although reversible data hiding technology is widely used, it still faces several challenges and issues. These include ensuring the security and reliability of embedded secret data, improving the embedding capacity, and maintaining the quality of media data. Additionally, irregular data types, such as three-dimensional point clouds and triangle mesh-represented 3D models, lack an ordered structure in their representation. As a result, embedding these irregular data into digital media does not provide sufficient information for the complete recovery of the original data during extraction. To address this issue, this paper proposes a method based on convolutional neural network prediction error expansion to enhance the embedding capacity of carrier images while maintaining acceptable visual quality. The triangle mesh representation of the 3D model is regularized in a two-dimensional parameterization domain, and the regularized 3D model is reversibly embedded into the image. The process of embedding and extracting confidential information in carrier images is symmetrical, and the regularization and restoration of 3D models are also symmetrical. Experiments show that the proposed method increases the reversible embedding capacity, and the triangle mesh can be conveniently subjected to reversible hiding.
- Open Access
- 21 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 248-252
Efficient Parallel Computation Of 3D Model Deformation Based On Conformal Mapping
In general, the animation between three-dimensional models uses linear interpolation between models to calculate the intermediate state. Before interpolation, the mapping relationship between the source model and the target model should be calculated to find the one-to-one correspondence of vertices. It is often necessary to traverse all vertices of the mesh in interpolation calculation, it can be difficult to implement parallel operation due to the irregularity of triangular mesh. This paper is aimed to form a regular representation of the 3D model in the conformal parameterization and set up efficient parallel computing under the regular structure so as to improve the efficiency of deformation computing of 3D models.
- 21 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 248-252
Open AccessEfficient Parallel Computation Of 3D Model Deformation Based On Conformal Mapping
In general, the animation between three-dimensional models uses linear interpolation between models to calculate the intermediate state. Before interpolation, the mapping relationship between the source model and the target model should be calculated to find the one-to-one correspondence of vertices. It is often necessary to traverse all vertices of the mesh in interpolation calculation, it can be difficult to implement parallel operation due to the irregularity of triangular mesh. This paper is aimed to form a regular representation of the 3D model in the conformal parameterization and set up efficient parallel computing under the regular structure so as to improve the efficiency of deformation computing of 3D models.
- Open Access
- 11 October 2022
- Published by Springer Nature in Research Square
Heteroscedastic-embedded Ensemble for Imbalanced Massive Data Classification
The imbalanced learning methods aim to learn the unbiased models from massive class-imbalanced datasets. However, due to the uncertainty of data distributions affected by noise and borderline samples, the models based on heuristic assumptions or meta learning often suffer from the lack of stability and practicability for real-world classification tasks which often uses the skewed dataset of low-quality. In order to effectively cope with these issues, in this work, we propose a novel heteroscedastic-embedded ensemble (HEE) for imbalanced massive data classification. We first design an effective task sensing strategy with data-dependent heteroscedastic to adaptively guide the sampler’s focus on informative samples, which makes the learning method much more robust for noisy data. Then, similar to the learning style of human beings, i.e., easy to difficult, the HEE framework gradually builds a strong ensemble classifier through interactions between harmonizing data resampling and model-training. The simulation results and analysis on both synthetic and real-world tasks demonstrate the effectiveness, robustness, and transferability of the proposed method.
- 11 October 2022
- Published by Springer Nature in Research Square
Open AccessHeteroscedastic-embedded Ensemble for Imbalanced Massive Data Classification
The imbalanced learning methods aim to learn the unbiased models from massive class-imbalanced datasets. However, due to the uncertainty of data distributions affected by noise and borderline samples, the models based on heuristic assumptions or meta learning often suffer from the lack of stability and practicability for real-world classification tasks which often uses the skewed dataset of low-quality. In order to effectively cope with these issues, in this work, we propose a novel heteroscedastic-embedded ensemble (HEE) for imbalanced massive data classification. We first design an effective task sensing strategy with data-dependent heteroscedastic to adaptively guide the sampler’s focus on informative samples, which makes the learning method much more robust for noisy data. Then, similar to the learning style of human beings, i.e., easy to difficult, the HEE framework gradually builds a strong ensemble classifier through interactions between harmonizing data resampling and model-training. The simulation results and analysis on both synthetic and real-world tasks demonstrate the effectiveness, robustness, and transferability of the proposed method.
- 1 January 2021
- Published by Journal of Applied Optics in Journal of Applied Optics
- Vol. 42 (4) , 656-663
Remote object image enhancement of fusion Retinex anddiscrete wavelet singular value decomposition
Aiming at the problem of low illumination degraded image enhancement obtained by remote imaging system, an image enhancement algorithm based on fusion Retinex and discrete wavelet singular value decomposition was proposed. In this method, the adaptive full-scale Retinex (AFSR) was used to coarsely extract the illumination and reflection components, and then the reflection components of the extracted image were decomposed into four frequency subbands by discrete wavelet transform, and the singular value matrix of the low-frequency subbands image was estimated. Finally, the inverse wavelet transform was adopted to precisely reconstruct the image. The experimental results show that the visual enhancement effect of the low illumination degraded image processed by the proposed method is better, which is superior to other classical algorithms in terms of objective evaluation indexes such as image contrast, information entropy, average gradient and edge density.
- 1 January 2021
- Published by Journal of Applied Optics in Journal of Applied Optics
- Vol. 42 (4) , 656-663
Remote object image enhancement of fusion Retinex anddiscrete wavelet singular value decomposition
Aiming at the problem of low illumination degraded image enhancement obtained by remote imaging system, an image enhancement algorithm based on fusion Retinex and discrete wavelet singular value decomposition was proposed. In this method, the adaptive full-scale Retinex (AFSR) was used to coarsely extract the illumination and reflection components, and then the reflection components of the extracted image were decomposed into four frequency subbands by discrete wavelet transform, and the singular value matrix of the low-frequency subbands image was estimated. Finally, the inverse wavelet transform was adopted to precisely reconstruct the image. The experimental results show that the visual enhancement effect of the low illumination degraded image processed by the proposed method is better, which is superior to other classical algorithms in terms of objective evaluation indexes such as image contrast, information entropy, average gradient and edge density.
- 7 July 2020
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 79 (35-36) , 25817-25834
Shape point set matching based on oriented shape context in turbulence-cluttered scene
- 7 July 2020
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 79 (35-36) , 25817-25834
Shape point set matching based on oriented shape context in turbulence-cluttered scene
- 10 December 2018
- Published by IOP Publishing in Journal of Optics
- Vol. 21 (1) , 015702
Geometric distortion correction of long-range imaging containing moving objects
Video sequences of long-range imaging are inevitably affected by optical turbulence, which leads to non-uniform geometric distortion and object position shifts. The restoration of this turbulence-degraded data containing moving objects is a challenging task, which essentially involves video stabilization and the detection of moving objects. In this work, a novel method is proposed for simultaneously realizing turbulence mitigation and moving objects detection. We firstly model the turbulent foreground with a specific mixture of Gaussian (MoG) distribution, which is regularized online by the low-rank subspace of the background. Then, to preserve the low-rank property of the dynamic background, we embed a transformation operator into the proposed model which makes it much more robust in the event of practical camera jitters or rotation. Finally, a simple mask strategy is used to reconstruct stable frames containing moving objects. Extensive experiments using synthetic and real-life turbulence-degraded data show that the proposed method outperforms other compared approaches in terms of both geometric distortion correction and the preservation of moving objects.
- 10 December 2018
- Published by IOP Publishing in Journal of Optics
- Vol. 21 (1) , 015702
Geometric distortion correction of long-range imaging containing moving objects
Video sequences of long-range imaging are inevitably affected by optical turbulence, which leads to non-uniform geometric distortion and object position shifts. The restoration of this turbulence-degraded data containing moving objects is a challenging task, which essentially involves video stabilization and the detection of moving objects. In this work, a novel method is proposed for simultaneously realizing turbulence mitigation and moving objects detection. We firstly model the turbulent foreground with a specific mixture of Gaussian (MoG) distribution, which is regularized online by the low-rank subspace of the background. Then, to preserve the low-rank property of the dynamic background, we embed a transformation operator into the proposed model which makes it much more robust in the event of practical camera jitters or rotation. Finally, a simple mask strategy is used to reconstruct stable frames containing moving objects. Extensive experiments using synthetic and real-life turbulence-degraded data show that the proposed method outperforms other compared approaches in terms of both geometric distortion correction and the preservation of moving objects.