Xie Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xie Han has a total of 80 co-authors. Here are the top co-authors by number of shared publications:
- Fengguang Xiong
Shanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, China
14 shared publications - Liqun Kuang
School of Computer Science and Technology, North University of China, Taiyuan, China
14 shared publications - Kewu Li
School of Electrical and Control Engineering, North University of China, Taiyuan 030051, China
5 shared publications - Ligang He
University of Warwick
5 shared publications - Lei Guo
Shanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, China
3 shared publications Ligang He
3 shared publications
Latest Publications
- 11 November 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 335
AdaStitch: Semantics-aware adaptive stabilization and stitching for binocular video
- 11 November 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 335
AdaStitch: Semantics-aware adaptive stabilization and stitching for binocular video
- 28 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
Physics-driven local-whole elastic deformation modeling for point cloud representation learning
- 28 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
Physics-driven local-whole elastic deformation modeling for point cloud representation learning
- Open Access
- 11 May 2026
- Published by MDPI AG in Algorithms
- Vol. 19 (5) , 380
MaLCA: Point Cloud Registration with Mamba-Enhanced Features and Local Correspondence Augmentation
High-quality correspondences are critical to the accuracy and robustness of point cloud registration. Existing Transformer-based methods are fundamentally constrained by the quadratic computational complexity of self-attention, resulting in limited scalability. Moreover, conventional outlier removal paradigms operate by pruning initial correspondences, and thus fail catastrophically in low-overlap scenarios where initial inliers are inherently scarce. To address these challenges, we propose MaLCA, a point cloud registration method based on Mamba-enhanced features and local correspondence augmentation. We first adopt KPFCN as the backbone to extract multi-scale geometric features from raw point clouds. A Mamba selective state space model then replaces self-attention for global context modeling with linear complexity, while cross-attention is retained to facilitate inter-point-cloud feature interaction. Rather than following the conventional subtraction-based outlier removal paradigm, we introduce a prior-guided local rematching strategy combined with a fused neighbor matching mechanism that iteratively constructs dense, high-quality correspondences from sparse initial inliers, fundamentally overcoming the bottleneck of inlier scarcity in challenging scenes. Extensive experiments on the 3DMatch/3DLoMatch and 4DMatch/4DLoMatch benchmarks demonstrate that MaLCA achieves competitive registration performance across both rigid and deformable scenarios, with particular advantages in low-overlap cases.
- 11 May 2026
- Published by MDPI AG in Algorithms
- Vol. 19 (5) , 380
Open AccessMaLCA: Point Cloud Registration with Mamba-Enhanced Features and Local Correspondence Augmentation
High-quality correspondences are critical to the accuracy and robustness of point cloud registration. Existing Transformer-based methods are fundamentally constrained by the quadratic computational complexity of self-attention, resulting in limited scalability. Moreover, conventional outlier removal paradigms operate by pruning initial correspondences, and thus fail catastrophically in low-overlap scenarios where initial inliers are inherently scarce. To address these challenges, we propose MaLCA, a point cloud registration method based on Mamba-enhanced features and local correspondence augmentation. We first adopt KPFCN as the backbone to extract multi-scale geometric features from raw point clouds. A Mamba selective state space model then replaces self-attention for global context modeling with linear complexity, while cross-attention is retained to facilitate inter-point-cloud feature interaction. Rather than following the conventional subtraction-based outlier removal paradigm, we introduce a prior-guided local rematching strategy combined with a fused neighbor matching mechanism that iteratively constructs dense, high-quality correspondences from sparse initial inliers, fundamentally overcoming the bottleneck of inlier scarcity in challenging scenes. Extensive experiments on the 3DMatch/3DLoMatch and 4DMatch/4DLoMatch benchmarks demonstrate that MaLCA achieves competitive registration performance across both rigid and deformable scenarios, with particular advantages in low-overlap cases.
- Open Access
- 16 October 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (10) , 648
Cosine Prompt-Based Class Incremental Semantic Segmentation for Point Clouds
Although current 3D semantic segmentation methods have achieved significant success, they suffer from catastrophic forgetting when confronted with dynamic, open environments. To address this issue, class incremental learning is introduced to update models while maintaining a balance between plasticity and stability. In this work, we propose CosPrompt, a rehearsal-free approach for class incremental semantic segmentation. Specifically, we freeze the prompts for existing classes and incrementally expand and fine-tune the prompts for new classes, thereby generating discriminative and customized features. We employ clamping operations to regulate backward propagation, ensuring smooth training. Furthermore, we utilize the learning without forgetting loss and pseudo-label generation to further mitigate catastrophic forgetting. We conduct comparative and ablation experiments on the S3DIS dataset and ScanNet v2 dataset, demonstrating the effectiveness and feasibility of our method.
- 16 October 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (10) , 648
Open AccessCosine Prompt-Based Class Incremental Semantic Segmentation for Point Clouds
Although current 3D semantic segmentation methods have achieved significant success, they suffer from catastrophic forgetting when confronted with dynamic, open environments. To address this issue, class incremental learning is introduced to update models while maintaining a balance between plasticity and stability. In this work, we propose CosPrompt, a rehearsal-free approach for class incremental semantic segmentation. Specifically, we freeze the prompts for existing classes and incrementally expand and fine-tune the prompts for new classes, thereby generating discriminative and customized features. We employ clamping operations to regulate backward propagation, ensuring smooth training. Furthermore, we utilize the learning without forgetting loss and pseudo-label generation to further mitigate catastrophic forgetting. We conduct comparative and ablation experiments on the S3DIS dataset and ScanNet v2 dataset, demonstrating the effectiveness and feasibility of our method.
- 20 August 2025
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 112
Multi-modal semantic embedding network for 3D shape recognition and retrieval
- 20 August 2025
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 112
Multi-modal semantic embedding network for 3D shape recognition and retrieval
- Open Access
- 24 June 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (7) , 383
Spatiotemporal Contextual 3D Semantic Segmentation for Intelligent Outdoor Mining
Three-dimensional semantic segmentation plays a crucial role in accurately identifying terrain features and objects by effectively extracting 3D spatial information from the environment. However, the inherent sparsity of point clouds and unclear terrain boundaries in outdoor mining environments significantly complicate the recognition process. To address these challenges, we propose a novel 3D semantic segmentation network that incorporates spatiotemporal feature aggregation. Specifically, we introduced the Gated Spatiotemporal Clue Encoder, which extracts spatiotemporal context from historical multi-frame point cloud data and combines it with the current scan frame to enhance feature representation. Additionally, the Spatiotemporal Feature State Space Module is proposed to efficiently model long-term spatiotemporal features while minimizing computational and memory overhead. Experimental results show that the proposed method outperforms the baseline model, achieving a 2.1% improvement in mIoU on the self-constructed TZMD_NUC outdoor mining dataset and a 1.9% avg improvement on the public SemanticKITTI dataset. Moreover, the method simultaneously improves computational efficiency, making it more suitable for real-time applications in complex, real-world mining environments. These results validate the effectiveness of the proposed method, offering a promising solution for 3D semantic segmentation in complex, real-world mining environments, where computational efficiency and accuracy are both critical.
- 24 June 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (7) , 383
Open AccessSpatiotemporal Contextual 3D Semantic Segmentation for Intelligent Outdoor Mining
Three-dimensional semantic segmentation plays a crucial role in accurately identifying terrain features and objects by effectively extracting 3D spatial information from the environment. However, the inherent sparsity of point clouds and unclear terrain boundaries in outdoor mining environments significantly complicate the recognition process. To address these challenges, we propose a novel 3D semantic segmentation network that incorporates spatiotemporal feature aggregation. Specifically, we introduced the Gated Spatiotemporal Clue Encoder, which extracts spatiotemporal context from historical multi-frame point cloud data and combines it with the current scan frame to enhance feature representation. Additionally, the Spatiotemporal Feature State Space Module is proposed to efficiently model long-term spatiotemporal features while minimizing computational and memory overhead. Experimental results show that the proposed method outperforms the baseline model, achieving a 2.1% improvement in mIoU on the self-constructed TZMD_NUC outdoor mining dataset and a 1.9% avg improvement on the public SemanticKITTI dataset. Moreover, the method simultaneously improves computational efficiency, making it more suitable for real-time applications in complex, real-world mining environments. These results validate the effectiveness of the proposed method, offering a promising solution for 3D semantic segmentation in complex, real-world mining environments, where computational efficiency and accuracy are both critical.
- Open Access
- 4 June 2025
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 11 (7) , 1-16
Fusing feature consistency across views for multi-view stereo
- 4 June 2025
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 11 (7) , 1-16
Open AccessFusing feature consistency across views for multi-view stereo
- Open Access
- 23 April 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-21
Frame points attention convolution for deep learning on point cloud
Point Cloud can be considered as non-Euclidean structure data since it is disordered and irregular. When training on point cloud, it is difficult to apply spatial discrete convolution directly. In this paper, we propose a novel three-dimensional spatial convolution operator called frame points attention convolution (FPAC). FPAC pre-defines a set of frame points in space and quantifies the correlation between the input local points and the frame points through an attention mechanism. FPAC then combines the quantified correlations with the weights of the frame points to generate spatially continuous filters. The convolution weights for different local areas in the filters are calculated dynamically, without relying on generative models or probabilistic assumptions. Furthermore, FPAC is reformulated to reduce the internal dimensions during training, which reduces memory consumption and significantly improves training speed. Several optimization measures are also implemented to further enhance the performance of FPAC. We built three common point cloud task networks using FPAC and conducted experiments to train these networks on widely used datasets. Experimental results show that the method proposed in this work is competitive with state-of-the-art methods for point cloud tasks.
- 23 April 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-21
Open AccessFrame points attention convolution for deep learning on point cloud
Point Cloud can be considered as non-Euclidean structure data since it is disordered and irregular. When training on point cloud, it is difficult to apply spatial discrete convolution directly. In this paper, we propose a novel three-dimensional spatial convolution operator called frame points attention convolution (FPAC). FPAC pre-defines a set of frame points in space and quantifies the correlation between the input local points and the frame points through an attention mechanism. FPAC then combines the quantified correlations with the weights of the frame points to generate spatially continuous filters. The convolution weights for different local areas in the filters are calculated dynamically, without relying on generative models or probabilistic assumptions. Furthermore, FPAC is reformulated to reduce the internal dimensions during training, which reduces memory consumption and significantly improves training speed. Several optimization measures are also implemented to further enhance the performance of FPAC. We built three common point cloud task networks using FPAC and conducted experiments to train these networks on widely used datasets. Experimental results show that the method proposed in this work is competitive with state-of-the-art methods for point cloud tasks.
- Open Access
- 9 April 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (8) , 4121
Focusing 3D Small Objects with Object Matching Set Abstraction
Currently, 3D object detection methods fail to detect small objects due to the fewer effective points of small objects. It is a significant challenge to reduce the loss of information of points in representation learning. To this end, we propose an effective 3D detection method with object matching set abstraction (OMSA). We observe that key points are lost during feature learning with multiple set abstraction layers, especially for downsampling and queries. Therefore, we present a novel sampling module named focus-based sampling, which raises the sampling probability of small objects. In addition, we design a multi-scale cube query to match the small objects with a close geometric alignment. Our comprehensive experimental evaluations on the KITTI 3D benchmark demonstrate significant performance improvements in 3D object detection. Notably, the proposed framework exhibits competitive detection accuracy for small objects (pedestrians and cyclists). Through an ablation study, we verify that each module contributes to the performance enhancement and demonstrate the robustness of the method against the balance factor.
- 9 April 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (8) , 4121
Open AccessFocusing 3D Small Objects with Object Matching Set Abstraction
Currently, 3D object detection methods fail to detect small objects due to the fewer effective points of small objects. It is a significant challenge to reduce the loss of information of points in representation learning. To this end, we propose an effective 3D detection method with object matching set abstraction (OMSA). We observe that key points are lost during feature learning with multiple set abstraction layers, especially for downsampling and queries. Therefore, we present a novel sampling module named focus-based sampling, which raises the sampling probability of small objects. In addition, we design a multi-scale cube query to match the small objects with a close geometric alignment. Our comprehensive experimental evaluations on the KITTI 3D benchmark demonstrate significant performance improvements in 3D object detection. Notably, the proposed framework exhibits competitive detection accuracy for small objects (pedestrians and cyclists). Through an ablation study, we verify that each module contributes to the performance enhancement and demonstrate the robustness of the method against the balance factor.
- Open Access
Focusing on Cracks with Instance Normalization Wavelet Layer
Automatic crack detection is challenging, owing to the complex and thin topologies, diversity, and background noises of cracks. Inspired by the wavelet theory, we present an instance normalization wavelet (INW) layer and embed the layer into the deep model for segmentation. The proposed layer employs prior knowledge in the wavelets to capture the crack features and filter the high-frequency noises simultaneously, accelerating the convergence of model training. Furthermore, instance normalization in our layer is utilized to mitigate the feature differences, boosting the generalization capability. In addition, a fusion layer is added to merge the information across the different layers. The comparison experiments and ablation studies demonstrate that the INW layer steadily enhances recognition and convergence performance on the DeepCrack dataset and CRACK500 dataset.
Open AccessFocusing on Cracks with Instance Normalization Wavelet Layer
Automatic crack detection is challenging, owing to the complex and thin topologies, diversity, and background noises of cracks. Inspired by the wavelet theory, we present an instance normalization wavelet (INW) layer and embed the layer into the deep model for segmentation. The proposed layer employs prior knowledge in the wavelets to capture the crack features and filter the high-frequency noises simultaneously, accelerating the convergence of model training. Furthermore, instance normalization in our layer is utilized to mitigate the feature differences, boosting the generalization capability. In addition, a fusion layer is added to merge the information across the different layers. The comparison experiments and ablation studies demonstrate that the INW layer steadily enhances recognition and convergence performance on the DeepCrack dataset and CRACK500 dataset.