Xiaoping Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaoping Liu has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Weijia Jia
Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, China
12 shared publications - Yang Zhao
Hefei University of Technology, Hefei, China
8 shared publications - Mingwei Cao
Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei 230601, China
7 shared publications - Dong Wang
School of Electronic and Information Engineering, Anhui Jianzhu University, Hefei, China
6 shared publications - Shujie Li
School of Software, Hefei University of Technology, Hefei, China
5 shared publications Yang Zhao
School of Computer and Information, Hefei University of Technology, Hefei, China
5 shared publications
Latest Publications
- 28 October 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42  (14) , 581
AesMaTF: an efficient Mamba-Transformer hybrid with diagonal selective scanning for image aesthetic assessment
- 28 October 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42  (14) , 581
AesMaTF: an efficient Mamba-Transformer hybrid with diagonal selective scanning for image aesthetic assessment
- Open Access
- 3 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
Controlling the Latent Diffusion Model for Generative Image Shadow Removal via Residual Generation
Large-scale generative models have achieved remarkable advancements in various visual tasks, yet their application to shadow removal in images remains challenging. These models often generate diverse, realistic details without adequate focus on fidelity, failing to meet the crucial requirements of shadow removal, which necessitates precise preservation of image content. In contrast to prior approaches that aimed to regenerate shadow-free images from scratch, this paper utilizes diffusion models to generate and refine image residuals. This strategy fully uses the inherent detailed information within shadowed images, resulting in a more efficient and faithful reconstruction of shadow-free content. Additionally, to prevent the accumulation of errors during the generation process, a cross-timestep self-enhancement training strategy is proposed. This strategy leverages the network itself to augment the training data, not only increasing the volume of data but also enabling the network to dynamically correct its generation trajectory, ensuring a more accurate and robust output. In addition, to address the loss of original details in the process of image encoding and decoding of large generative models, a content-preserved encoder-decoder structure is designed with a control mechanism and multi-scale skip connections to achieve high-fidelity shadow-free image reconstruction. Experimental results demonstrate that the proposed method can reproduce high-quality results based on a large latent diffusion prior and faithfully preserve the original contents in shadow regions.
- 3 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
Open AccessControlling the Latent Diffusion Model for Generative Image Shadow Removal via Residual Generation
Large-scale generative models have achieved remarkable advancements in various visual tasks, yet their application to shadow removal in images remains challenging. These models often generate diverse, realistic details without adequate focus on fidelity, failing to meet the crucial requirements of shadow removal, which necessitates precise preservation of image content. In contrast to prior approaches that aimed to regenerate shadow-free images from scratch, this paper utilizes diffusion models to generate and refine image residuals. This strategy fully uses the inherent detailed information within shadowed images, resulting in a more efficient and faithful reconstruction of shadow-free content. Additionally, to prevent the accumulation of errors during the generation process, a cross-timestep self-enhancement training strategy is proposed. This strategy leverages the network itself to augment the training data, not only increasing the volume of data but also enabling the network to dynamically correct its generation trajectory, ensuring a more accurate and robust output. In addition, to address the loss of original details in the process of image encoding and decoding of large generative models, a content-preserved encoder-decoder structure is designed with a control mechanism and multi-scale skip connections to achieve high-fidelity shadow-free image reconstruction. Experimental results demonstrate that the proposed method can reproduce high-quality results based on a large latent diffusion prior and faithfully preserve the original contents in shadow regions.
- 31 July 2026
- Published by Elsevier in Pattern Recognition
- Vol. 180
Open-VSRD: A large-scale dynamic dataset and diffusion framework for video shadow removal
- 31 July 2026
- Published by Elsevier in Pattern Recognition
- Vol. 180
Open-VSRD: A large-scale dynamic dataset and diffusion framework for video shadow removal
- Open Access
- 25 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open-VSRD: A Large-Scale Dynamic Dataset and Diffusion Framework for Video Shadow Removal
Video shadow removal remains a challenging and underexplored task due to the lack of large-scale datasets and open-source benchmarks. To address this gap, we present Open Video Shadow Removal Dataset (Open-VSRD), the first publicly available dataset for video shadow removal, accompanied by a dedicated video diffusion framework designed specifically for multi-frame shadow removal. Open-VSRD is a large-scale synthetic dataset built using the Unity engine, consisting of 5,932 training clips and 244 testing clips captured from diverse scenes. It features a wide range of dynamic scenarios involving various moving objects, complex camera motions, and heterogeneous lighting conditions, offering rich spatial–temporal and illumination variations essential for robust model training and evaluation. Building upon this dataset, we propose a video diffusion method based on {alternating bidirectional diffusion guidance} strategy that enhances temporal stability specifically within shadow regions while maintaining overall visual coherence. Furthermore, a temporal VAE (variational autoencoder) decoder is designed to leverage multi-scale latent features from a frozen encoder, significantly improving reconstruction fidelity and temporal consistency. Extensive experiments demonstrate that our method substantially outperforms existing single-frame shadow removal approaches, validating both the effectiveness of the proposed framework and the significance of the Open-VSRD dataset. Datasets and codes will be publicly released.
- 25 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessOpen-VSRD: A Large-Scale Dynamic Dataset and Diffusion Framework for Video Shadow Removal
Video shadow removal remains a challenging and underexplored task due to the lack of large-scale datasets and open-source benchmarks. To address this gap, we present Open Video Shadow Removal Dataset (Open-VSRD), the first publicly available dataset for video shadow removal, accompanied by a dedicated video diffusion framework designed specifically for multi-frame shadow removal. Open-VSRD is a large-scale synthetic dataset built using the Unity engine, consisting of 5,932 training clips and 244 testing clips captured from diverse scenes. It features a wide range of dynamic scenarios involving various moving objects, complex camera motions, and heterogeneous lighting conditions, offering rich spatial–temporal and illumination variations essential for robust model training and evaluation. Building upon this dataset, we propose a video diffusion method based on {alternating bidirectional diffusion guidance} strategy that enhances temporal stability specifically within shadow regions while maintaining overall visual coherence. Furthermore, a temporal VAE (variational autoencoder) decoder is designed to leverage multi-scale latent features from a frozen encoder, significantly improving reconstruction fidelity and temporal consistency. Extensive experiments demonstrate that our method substantially outperforms existing single-frame shadow removal approaches, validating both the effectiveness of the proposed framework and the significance of the Open-VSRD dataset. Datasets and codes will be publicly released.
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10  (2) , 1892-1904
PSINet: Parallel Space Interaction Network for Human Pose Estimation
Human pose estimation is sensitive to the spatial resolution of feature representations in a single image. While multi-scale features are often exploited to improve keypoint localization, the effectiveness of parallel spatial learning across multiple uniform-sized spaces remains underexplored. To address this, To address this, we propose the Parallel Space Interaction Network (PSINet), which splits input features into multiple identical parallel spaces to facilitate efficient spatial feature learning for human pose estimation. Based on the multiple spaces, we refine the vanilla vision Transformer by proposing a Split-Head Transformer (SHT) to enhance global interaction within parallel spaces. Furthermore, we introduce Parallel Space Fusion instrument to strengthen the capacity of the PSINet by acquiring the relationship between multiple parallel spaces. Extensive experiments demonstrate that PSINet achieves state-of-the-art accuracy after data augmentation, running at 180 FPS on a single GTX2080Ti, offering a superior trade-off between accuracy and efficiency.
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10  (2) , 1892-1904
PSINet: Parallel Space Interaction Network for Human Pose Estimation
Human pose estimation is sensitive to the spatial resolution of feature representations in a single image. While multi-scale features are often exploited to improve keypoint localization, the effectiveness of parallel spatial learning across multiple uniform-sized spaces remains underexplored. To address this, To address this, we propose the Parallel Space Interaction Network (PSINet), which splits input features into multiple identical parallel spaces to facilitate efficient spatial feature learning for human pose estimation. Based on the multiple spaces, we refine the vanilla vision Transformer by proposing a Split-Head Transformer (SHT) to enhance global interaction within parallel spaces. Furthermore, we introduce Parallel Space Fusion instrument to strengthen the capacity of the PSINet by acquiring the relationship between multiple parallel spaces. Extensive experiments demonstrate that PSINet achieves state-of-the-art accuracy after data augmentation, running at 180 FPS on a single GTX2080Ti, offering a superior trade-off between accuracy and efficiency.
- 24 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22  (7) , 5712-5723
WG-Net: Wireframe Generation From Noisy Point Cloud by Edge Primitive Fitting
3-Dscanning has various applications in industrial design. However, the noisy point clouds being generated are difficult to be used in the applications directly. The ease of editing and lightweight nature of wireframes make it highly suitable for industrial design. To address this issue, WG-Net is proposed for generating wireframes from noisy point clouds. An edge primitive detection network that includes a multilevel feature extraction module and a feature fusion module is designed for point classification, primitive segmentation, and displacement vector prediction. Based on the classification and segmentation results of edge points, targeted fitting methods are applied to accurately fit each category of edge primitives, ensuring precise geometric representation. Finally, fitting results are integrated into a complete wireframe structure. Through extensive experiments on computer-aided design datasets, WG-Net achieved significant performance improvements compared to state-of-the-art methods. In addition, we have verified the feasibility and practical applicability of WG-Net on real scanned data.
- 24 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22  (7) , 5712-5723
WG-Net: Wireframe Generation From Noisy Point Cloud by Edge Primitive Fitting
3-Dscanning has various applications in industrial design. However, the noisy point clouds being generated are difficult to be used in the applications directly. The ease of editing and lightweight nature of wireframes make it highly suitable for industrial design. To address this issue, WG-Net is proposed for generating wireframes from noisy point clouds. An edge primitive detection network that includes a multilevel feature extraction module and a feature fusion module is designed for point classification, primitive segmentation, and displacement vector prediction. Based on the classification and segmentation results of edge points, targeted fitting methods are applied to accurately fit each category of edge primitives, ensuring precise geometric representation. Finally, fitting results are integrated into a complete wireframe structure. Through extensive experiments on computer-aided design datasets, WG-Net achieved significant performance improvements compared to state-of-the-art methods. In addition, we have verified the feasibility and practical applicability of WG-Net on real scanned data.
- Top Cited PapersOpen Access
- 13 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22  (1) , 1-21
MatPose: A 2D Human Pose Estimation Model with Hybrid Mamba-Transformer
Recently, Mamba has gained widespread attention due to its ability to model long-range dependencies with linear computational complexity. To explore the application of Mamba in 2D human pose estimation, we propose MatPose, a Mamba-Transformer hybrid model specifically designed for efficient 2D human pose estimation. The model aims to combine Mamba’s efficient modeling of long-range dependencies with the powerful global context modeling capabilities of the Transformer to effectively extract human pose keypoints. Initially, to address the lack of local features when Mamba is applied to computer vision tasks, we design a Cross-Stage Multi-Scale Convolution (CSMSC) module by integrating multi-scale convolution, cross-stage feature fusion, and spatial attention mechanisms to effectively extract local features. Then, to mitigate the long-range forgetting issue inherent in Mamba, we shorten the sequence length using the Conv-Reduce operation. In addition, we design a Channel Selection Attention (CSA) mechanism to compensate for the feature loss caused by the Conv-Reduce operation. Finally, to explore a suitable integration method for the Mamba-Transformer hybrid model in 2D human pose estimation, we conduct a comprehensive ablation study on the feasibility of integrating Mamba and Transformer models. Experimental results show that the proposed method, compared to the baseline model, improves performance while reducing computational overhead. On the COCO val2017 dataset, MatPose achieves an AP of 74.6 with only 5.18 GFLOPs, outperforming most existing human pose estimation models.
- 13 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22  (1) , 1-21
Top Cited PapersOpen AccessMatPose: A 2D Human Pose Estimation Model with Hybrid Mamba-Transformer
Recently, Mamba has gained widespread attention due to its ability to model long-range dependencies with linear computational complexity. To explore the application of Mamba in 2D human pose estimation, we propose MatPose, a Mamba-Transformer hybrid model specifically designed for efficient 2D human pose estimation. The model aims to combine Mamba’s efficient modeling of long-range dependencies with the powerful global context modeling capabilities of the Transformer to effectively extract human pose keypoints. Initially, to address the lack of local features when Mamba is applied to computer vision tasks, we design a Cross-Stage Multi-Scale Convolution (CSMSC) module by integrating multi-scale convolution, cross-stage feature fusion, and spatial attention mechanisms to effectively extract local features. Then, to mitigate the long-range forgetting issue inherent in Mamba, we shorten the sequence length using the Conv-Reduce operation. In addition, we design a Channel Selection Attention (CSA) mechanism to compensate for the feature loss caused by the Conv-Reduce operation. Finally, to explore a suitable integration method for the Mamba-Transformer hybrid model in 2D human pose estimation, we conduct a comprehensive ablation study on the feasibility of integrating Mamba and Transformer models. Experimental results show that the proposed method, compared to the baseline model, improves performance while reducing computational overhead. On the COCO val2017 dataset, MatPose achieves an AP of 74.6 with only 5.18 GFLOPs, outperforming most existing human pose estimation models.
- 27 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-13
RR-Net: 3-D Roof Reconstruction From Airborne LiDAR Point Clouds via Edge Segmentation and Wireframe Generation
Reconstruction of 3D roof from airborne LiDAR point clouds is an important task in the field of remote sensing and photogrammetry. Due to the high noise, large volume, and structural complexity inherent in LiDAR point clouds, traditional point cloud processing methods have limited performance in terms of accuracy and robustness. Most existing methods rely on corner point detection and edge prediction to extract and reconstruct roof structures. However, corner points are often sparsely distributed and difficult to locate precisely, resulting in noticeable geometric deviations and incomplete structural reconstruction. Therefore, generating high-quality 3D roof from complex LiDAR point clouds is still a challenging problem to be solved. To address these issues, we propose a novel roof reconstruction method RR-Net that combines edge segmentation and wireframe generation. Firstly, an innovative unified point cloud edge segmentation network was developed, achieving integrated edge detection, segmentation, and denoising. Secondly, based on the segmentation results from this network, an efficient and robust pipeline for wireframe generation and roof reconstruction was designed, enabling automated transformation from airborne LiDAR point clouds to roof models. Extensive experiments on the Building dataset demonstrate that RR-Net can efficiently and accurately reconstruct roofs from airborne LiDAR point clouds. RR-Net achieves 95.7% accuracy in edge detection and reduces the chamfer distance (CD) error of the wireframe to 0.021. The results of RR-Net are publicly available at: https://yecoxu.github.io/publications/RR-Net/.
- 27 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-13
RR-Net: 3-D Roof Reconstruction From Airborne LiDAR Point Clouds via Edge Segmentation and Wireframe Generation
Reconstruction of 3D roof from airborne LiDAR point clouds is an important task in the field of remote sensing and photogrammetry. Due to the high noise, large volume, and structural complexity inherent in LiDAR point clouds, traditional point cloud processing methods have limited performance in terms of accuracy and robustness. Most existing methods rely on corner point detection and edge prediction to extract and reconstruct roof structures. However, corner points are often sparsely distributed and difficult to locate precisely, resulting in noticeable geometric deviations and incomplete structural reconstruction. Therefore, generating high-quality 3D roof from complex LiDAR point clouds is still a challenging problem to be solved. To address these issues, we propose a novel roof reconstruction method RR-Net that combines edge segmentation and wireframe generation. Firstly, an innovative unified point cloud edge segmentation network was developed, achieving integrated edge detection, segmentation, and denoising. Secondly, based on the segmentation results from this network, an efficient and robust pipeline for wireframe generation and roof reconstruction was designed, enabling automated transformation from airborne LiDAR point clouds to roof models. Extensive experiments on the Building dataset demonstrate that RR-Net can efficiently and accurately reconstruct roofs from airborne LiDAR point clouds. RR-Net achieves 95.7% accuracy in edge detection and reduces the chamfer distance (CD) error of the wireframe to 0.021. The results of RR-Net are publicly available at: https://yecoxu.github.io/publications/RR-Net/.
- 23 October 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 299
MLENet: Multi-level efficient network based on single-scale feature extraction for human keypoint estimation
- 23 October 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 299
MLENet: Multi-level efficient network based on single-scale feature extraction for human keypoint estimation
- 23 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74  (00189456) , 1-15
Efficient Dual-Scale Cross-Attention Network for Human Pose Estimation
Human pose estimation has witnessed substantial advancements with the utilization of the Vision Transformer (ViT), which can accurately measure keypoint positions by leveraging ViT’s ability to extract global features. While increasing the depth or width of the self-attention mechanism can improve the accuracy of joint measurement, it inevitably results in higher computational complexity. This article presents an efficient dual-scale cross-attention network (EDCNet) for the precise human keypoint measurement. EDCNet incorporates a space split module (SSM) and a dual-scale cross-attention module (DCM), striking a more favorable balance between efficiency and accuracy compared to the conventional stacking of vanilla ViT. At the core of DCM lies a novel structure termed the channel-spatial ViT (CSViT). By leveraging the cross-attention mechanism formed by dual-scale CSViT, DCM effectively captures both local and global spatial dependencies. Specifically, CSViT utilizes a spatial activation unit (SAU) to amalgamate independent spatial information from the query, key, and value, effectively integrating both short- and long-range dependencies. Concurrently, we introduce a channel activation unit (CAU) within CSViT to enhance channel awareness through successive convolutions. Moreover, the SSM facilitates access to multispatial features through cost-effective spatial splitting, in conjunction with DCM, enhancing the overall performance of EDCNet. Extensive experiments on the COCO and MPII benchmarks demonstrate the effectiveness of our proposed EDCNet, obtaining 74.6 and 91.9 AP on COCO val and MPII val, respectively, which achieves superior performance with fewer parameters and lower computational costs than state-of-the-art methods.
- 23 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74  (00189456) , 1-15
Efficient Dual-Scale Cross-Attention Network for Human Pose Estimation
Human pose estimation has witnessed substantial advancements with the utilization of the Vision Transformer (ViT), which can accurately measure keypoint positions by leveraging ViT’s ability to extract global features. While increasing the depth or width of the self-attention mechanism can improve the accuracy of joint measurement, it inevitably results in higher computational complexity. This article presents an efficient dual-scale cross-attention network (EDCNet) for the precise human keypoint measurement. EDCNet incorporates a space split module (SSM) and a dual-scale cross-attention module (DCM), striking a more favorable balance between efficiency and accuracy compared to the conventional stacking of vanilla ViT. At the core of DCM lies a novel structure termed the channel-spatial ViT (CSViT). By leveraging the cross-attention mechanism formed by dual-scale CSViT, DCM effectively captures both local and global spatial dependencies. Specifically, CSViT utilizes a spatial activation unit (SAU) to amalgamate independent spatial information from the query, key, and value, effectively integrating both short- and long-range dependencies. Concurrently, we introduce a channel activation unit (CAU) within CSViT to enhance channel awareness through successive convolutions. Moreover, the SSM facilitates access to multispatial features through cost-effective spatial splitting, in conjunction with DCM, enhancing the overall performance of EDCNet. Extensive experiments on the COCO and MPII benchmarks demonstrate the effectiveness of our proposed EDCNet, obtaining 74.6 and 91.9 AP on COCO val and MPII val, respectively, which achieves superior performance with fewer parameters and lower computational costs than state-of-the-art methods.