Wei Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wei Li has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Jie Liu
School of Software, Nanchang University, Nanchang 330031, China
2 shared publications - Xiaolong Xie
School of Mathematics and Computer Science, Nanchang University, Nanchang 330031, China
2 shared publications - Cheng Wang
Fujian Key Laboratory of Sensing and Computing for Smart Cities, Xiamen University, Xiamen, Fujian, China
1 shared publication - Chenglu Wen
Xiamen University
1 shared publication - Hai-Ping Zhong
School of Mathematics and Computer, Yuzhang Normal University, Nanchang 330103, China
1 shared publication - Hong Jia
Fujian Key Laboratory of Sensing and Computing for Smart Cities, School of Informatics, Xiamen University, Xiamen 361005, China
1 shared publication
Latest Publications
- 17 October 2026
- Published by Springer Nature
- p. 433-452
PointCBA-TGRP: Clean-Label Backdoor Trigger Generation for Point Cloud via Regular Octahedron Partitioning
- 17 October 2026
- Published by Springer Nature
- p. 433-452
PointCBA-TGRP: Clean-Label Backdoor Trigger Generation for Point Cloud via Regular Octahedron Partitioning
- 1 September 2026
- Published by Springer Nature in Medical & Biological Engineering & Computing
- Vol. 64 (10) , 3769-3782
Neighbor-constrained attention for multiple instance learning in whole-slide histopathology
- 1 September 2026
- Published by Springer Nature in Medical & Biological Engineering & Computing
- Vol. 64 (10) , 3769-3782
Neighbor-constrained attention for multiple instance learning in whole-slide histopathology
- Open Access
- 15 August 2026
- Published by MDPI AG in Electronics
- Vol. 15 (16) , 3641
DAPR: Dynamic Distribution-Aware and Adaptive Pseudo-Label Refinement for Long-Tailed Semi-Supervised Oral Disease Classification
Oral disease image classification can support computer-assisted assessment of intraoral images. However, obtaining large-scale annotated medical data is expensive, while real-world oral disease datasets often exhibit severe long-tailed distributions, where minority disease categories contain only limited samples. Existing semi-supervised learning methods commonly rely on fixed-threshold pseudo labels and may produce prediction distributions dominated by majority classes, resulting in class bias and pseudo-label noise accumulation under long-tailed settings. To address these issues, we propose DAPR, a Distribution-Aware and Adaptive Pseudo-Label Refinement framework for long-tailed semi-supervised oral disease classification. DAPR employs Dynamic Category Distribution Modeling (DCDM) to track the evolving prediction distribution of unlabeled samples and generate distribution-aware soft pseudo labels. A class-adaptive dynamic thresholding (CADT) mechanism was further introduced to improve minority-class sample utilization. In addition, Relation-aware Representation Learning (RRL) aligns semantic and feature relationships to enhance feature discrimination. Experiments using stratified five-fold cross-validation on a long-tailed oral disease dataset show that DAPR achieves the highest average Accuracy and Macro-F1 among the compared methods under the evaluated setting. DAPR achieves the highest average Accuracy and Macro-F1 among the compared methods and obtains strong aggregate tail-class performance, particularly for Tooth Discoloration and Ulcers. These results indicate that DAPR improves aggregate class-balanced learning under the evaluated dataset, annotation ratio, and backbone configuration.
- 15 August 2026
- Published by MDPI AG in Electronics
- Vol. 15 (16) , 3641
Open AccessDAPR: Dynamic Distribution-Aware and Adaptive Pseudo-Label Refinement for Long-Tailed Semi-Supervised Oral Disease Classification
Oral disease image classification can support computer-assisted assessment of intraoral images. However, obtaining large-scale annotated medical data is expensive, while real-world oral disease datasets often exhibit severe long-tailed distributions, where minority disease categories contain only limited samples. Existing semi-supervised learning methods commonly rely on fixed-threshold pseudo labels and may produce prediction distributions dominated by majority classes, resulting in class bias and pseudo-label noise accumulation under long-tailed settings. To address these issues, we propose DAPR, a Distribution-Aware and Adaptive Pseudo-Label Refinement framework for long-tailed semi-supervised oral disease classification. DAPR employs Dynamic Category Distribution Modeling (DCDM) to track the evolving prediction distribution of unlabeled samples and generate distribution-aware soft pseudo labels. A class-adaptive dynamic thresholding (CADT) mechanism was further introduced to improve minority-class sample utilization. In addition, Relation-aware Representation Learning (RRL) aligns semantic and feature relationships to enhance feature discrimination. Experiments using stratified five-fold cross-validation on a long-tailed oral disease dataset show that DAPR achieves the highest average Accuracy and Macro-F1 among the compared methods under the evaluated setting. DAPR achieves the highest average Accuracy and Macro-F1 among the compared methods and obtains strong aggregate tail-class performance, particularly for Tooth Discoloration and Ulcers. These results indicate that DAPR improves aggregate class-balanced learning under the evaluated dataset, annotation ratio, and backbone configuration.
- Open Access
- 18 November 2025
- Published by MDPI AG in Electronics
- Vol. 14 (22) , 4512
3D Human Reconstruction from Monocular Vision Based on Neural Fields and Explicit Mesh Optimization
Three-dimensional Human Reconstruction from Monocular Vision is a key technology in Virtual Reality and digital humans. It aims to recover the 3D structure and pose of the human body from 2D images or video. Current methods for dynamic 3D reconstruction of the human body, which are based on monocular views, have low accuracy and remain a challenging problem. This paper proposes a fast reconstruction method based on Instant Human Model (IHM) generation, which achieves highly realistic 3D reconstruction of the human body in arbitrary poses. First, the efficient dynamic human body reconstruction method, InstantAvatar, is utilized to learn the shape and appearance of the human body in different poses. However, due to its direct use of low-resolution voxels as canonical spatial human representations, it is not possible to achieve satisfactory reconstruction results on a wide range of datasets. Next, a voxel occupancy grid is initialized in the A-pose, and a voxel attention mechanism module is constructed to enhance the reconstruction effect. Finally, the Instant Human Model (IHM) method is employed to define continuous fields on the surface, enabling highly realistic dynamic 3D human reconstruction. Experimental results show that, compared to the representative InstantAvatar method, IHM achieves a 0.1% improvement in SSIM and a 2% improvement in PSNR on the PeopleSnapshot benchmark dataset, demonstrating improvements in both reconstruction quality and detail. Specifically, IHM, through voxel attention mechanisms and Mesh adaptive iterative optimization, achieves highly realistic 3D mesh models of human bodies in various poses while ensuring efficiency.
- 18 November 2025
- Published by MDPI AG in Electronics
- Vol. 14 (22) , 4512
Open Access3D Human Reconstruction from Monocular Vision Based on Neural Fields and Explicit Mesh Optimization
Three-dimensional Human Reconstruction from Monocular Vision is a key technology in Virtual Reality and digital humans. It aims to recover the 3D structure and pose of the human body from 2D images or video. Current methods for dynamic 3D reconstruction of the human body, which are based on monocular views, have low accuracy and remain a challenging problem. This paper proposes a fast reconstruction method based on Instant Human Model (IHM) generation, which achieves highly realistic 3D reconstruction of the human body in arbitrary poses. First, the efficient dynamic human body reconstruction method, InstantAvatar, is utilized to learn the shape and appearance of the human body in different poses. However, due to its direct use of low-resolution voxels as canonical spatial human representations, it is not possible to achieve satisfactory reconstruction results on a wide range of datasets. Next, a voxel occupancy grid is initialized in the A-pose, and a voxel attention mechanism module is constructed to enhance the reconstruction effect. Finally, the Instant Human Model (IHM) method is employed to define continuous fields on the surface, enabling highly realistic dynamic 3D human reconstruction. Experimental results show that, compared to the representative InstantAvatar method, IHM achieves a 0.1% improvement in SSIM and a 2% improvement in PSNR on the PeopleSnapshot benchmark dataset, demonstrating improvements in both reconstruction quality and detail. Specifically, IHM, through voxel attention mechanisms and Mesh adaptive iterative optimization, achieves highly realistic 3D mesh models of human bodies in various poses while ensuring efficiency.
- Open Access
Two-Dimensional Skeleton Intersection Extraction-Based Method for Detecting Welded Joints on the Three-Dimensional Point Cloud of Sieve Nets
The concept of symmetry is a fundamental principle in various scientific and engineering fields, including welding technology. In the context of this paper, symmetry could play a role in optimizing the welding trajectory. Welding trajectory point detection relies on machine vision perception and intelligent algorithms to extract welding trajectory, which is crucial for the automatic welding of steel parts. However, in practice, sieve-net welding still relies on manual or semi-automatic operations, which have limitations, such as fixed positions and sizes, making it unsafe and inefficient. This paper proposes a 2D skeleton extraction algorithm for detecting weld joints in a sieve-net point cloud. First, the algorithm applies principal component analysis (PCA) to transform the point cloud and projects it into a 2D image with minimal information loss. Second, the expansion corrosion method is then employed to enhance the connectivity and refinement of the sieve-net mesh to serve the extraction of 2D skeleton. Third, the algorithm extracts the skeleton of the sieve-net grid and detects solder points. The average detection accuracy of the proposed algorithm is over 95%, which confirms its feasibility and practical application value in sieve-net welding.
Open AccessTwo-Dimensional Skeleton Intersection Extraction-Based Method for Detecting Welded Joints on the Three-Dimensional Point Cloud of Sieve Nets
The concept of symmetry is a fundamental principle in various scientific and engineering fields, including welding technology. In the context of this paper, symmetry could play a role in optimizing the welding trajectory. Welding trajectory point detection relies on machine vision perception and intelligent algorithms to extract welding trajectory, which is crucial for the automatic welding of steel parts. However, in practice, sieve-net welding still relies on manual or semi-automatic operations, which have limitations, such as fixed positions and sizes, making it unsafe and inefficient. This paper proposes a 2D skeleton extraction algorithm for detecting weld joints in a sieve-net point cloud. First, the algorithm applies principal component analysis (PCA) to transform the point cloud and projects it into a 2D image with minimal information loss. Second, the expansion corrosion method is then employed to enhance the connectivity and refinement of the sieve-net mesh to serve the extraction of 2D skeleton. Third, the algorithm extracts the skeleton of the sieve-net grid and detects solder points. The average detection accuracy of the proposed algorithm is over 95%, which confirms its feasibility and practical application value in sieve-net welding.
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-11
QPCR: Weakly Supervised Semantic Segmentation of Large-Scale Point Cloud via Gradual Query Points Component Reasoning
Semantic segmentation of large-scale point clouds under weak supervision is challenging due to the limited annotations. Current methods typically rely on the implicit use of annotation information to supervise the network, thereby constraining the capacity to characterize features at annotation points. In this article, we propose a query points component reasoning (QPCR) framework, which enhances the utilization of annotation information by introducing them into the middle layer, thereby refining the features used for semantic segmentation. First, we propose the semantic annotations component code reasoning (SACC Reasoning) module, which uses annotations of query points to supervise the semantic information of gradual query points. The semantic annotations component code (SACC) Reasoning module can guide the learning of feature representations of semantic annotations at multiple scales. Second, we create the semantic primitive component code reasoning (SPCC Reasoning) module, which addresses the issue of supervising the network using existing annotation point information that may suppress active features. The semantic primitive component code (SPCC) Reasoning module infers semantic primitive labels of query points using the decoding layer and uses them to guide the corresponding coding layer in learning semantic primitives. Finally, our QPCR method achieves state-of-the-art (SOTA) results on public benchmark datasets. Specifically, even with only 1% of annotated points, our QPCR method achieves the highest mIoU accuracy, i.e., 65.4% on S3DIS Area 5, 56.4% on SensatUrban and 55.3% mIoU on SemanticKITTI, respectively.
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-11
QPCR: Weakly Supervised Semantic Segmentation of Large-Scale Point Cloud via Gradual Query Points Component Reasoning
Semantic segmentation of large-scale point clouds under weak supervision is challenging due to the limited annotations. Current methods typically rely on the implicit use of annotation information to supervise the network, thereby constraining the capacity to characterize features at annotation points. In this article, we propose a query points component reasoning (QPCR) framework, which enhances the utilization of annotation information by introducing them into the middle layer, thereby refining the features used for semantic segmentation. First, we propose the semantic annotations component code reasoning (SACC Reasoning) module, which uses annotations of query points to supervise the semantic information of gradual query points. The semantic annotations component code (SACC) Reasoning module can guide the learning of feature representations of semantic annotations at multiple scales. Second, we create the semantic primitive component code reasoning (SPCC Reasoning) module, which addresses the issue of supervising the network using existing annotation point information that may suppress active features. The semantic primitive component code (SPCC) Reasoning module infers semantic primitive labels of query points using the decoding layer and uses them to guide the corresponding coding layer in learning semantic primitives. Finally, our QPCR method achieves state-of-the-art (SOTA) results on public benchmark datasets. Specifically, even with only 1% of annotated points, our QPCR method achieves the highest mIoU accuracy, i.e., 65.4% on S3DIS Area 5, 56.4% on SensatUrban and 55.3% mIoU on SemanticKITTI, respectively.
- 1 July 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 33 (04) , 043018-14
Temporal residual neural radiance fields for monocular video dynamic human body reconstruction
In the field of computer vision and graphics, high-quality reconstruction of the human body in static scenes has been achieved in recent years by a single multilayer perceptron (MLP) in a number of approaches. However, MLPs have capacity limitations, requiring substantial training time and computational resources for dynamic scene reconstruction, and the quality of reconstruction is significantly constrained. We propose a method for effectively processing complex spatiotemporal signals in dynamic scene human three-dimensional (3D) modeling. The proposed method uses temporal residual neural radiance fields to achieve novel view rendering and new pose synthesis of human bodies. To address the problem of representing temporal signals in video sequences, we construct a temporal residual field that is not related to the MLP architecture. Second, to improve the reconstruction efficiency, we propose an integrated approach that reduces the trainable parameters and accelerates rendering, thereby enhancing the network’s feature representation capability. Finally, we design a multi-dimensional loss function to accurately measure the loss between predicted and actual spatial pixel values. The experimental results show that our proposed approach improves the peak signal-to-noise ratio and structural similarity index accuracy metrics compared with the latest representative methods. It maintains a similar accuracy to Anim-NeRF and Neural Body while achieving a nearly 780-fold increase in time efficiency.
- 1 July 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 33 (04) , 043018-14
Temporal residual neural radiance fields for monocular video dynamic human body reconstruction
In the field of computer vision and graphics, high-quality reconstruction of the human body in static scenes has been achieved in recent years by a single multilayer perceptron (MLP) in a number of approaches. However, MLPs have capacity limitations, requiring substantial training time and computational resources for dynamic scene reconstruction, and the quality of reconstruction is significantly constrained. We propose a method for effectively processing complex spatiotemporal signals in dynamic scene human three-dimensional (3D) modeling. The proposed method uses temporal residual neural radiance fields to achieve novel view rendering and new pose synthesis of human bodies. To address the problem of representing temporal signals in video sequences, we construct a temporal residual field that is not related to the MLP architecture. Second, to improve the reconstruction efficiency, we propose an integrated approach that reduces the trainable parameters and accelerates rendering, thereby enhancing the network’s feature representation capability. Finally, we design a multi-dimensional loss function to accurately measure the loss between predicted and actual spatial pixel values. The experimental results show that our proposed approach improves the peak signal-to-noise ratio and structural similarity index accuracy metrics compared with the latest representative methods. It maintains a similar accuracy to Anim-NeRF and Neural Body while achieving a nearly 780-fold increase in time efficiency.
- Open Access
- 24 October 2023
- Published by MDPI AG in Electronics
- Vol. 12 (21) , 4382
Deform2NeRF: Non-Rigid Deformation and 2D–3D Feature Fusion with Cross-Attention for Dynamic Human Reconstruction
Reconstructing dynamic human body models from multi-view videos poses a substantial challenge in the field of 3D computer vision. Currently, the Animatable NeRF method addresses this challenge by mapping observed points from the viewing space to a canonical space. However, this mapping introduces positional shifts in predicted points, resulting in artifacts, particularly in intricate areas. In this paper, we propose an innovative approach called Deform2NeRF that incorporates non-rigid deformation correction and image feature fusion modules into the Animatable NeRF framework to enhance the reconstruction of animatable human models. Firstly, we introduce a non-rigid deformation field network to address the issue of point position shift effectively. This network adeptly corrects positional discrepancies caused by non-rigid deformations. Secondly, we introduce a 2D–3D feature fusion learning module with cross-attention and integrate it with the NeRF network to mitigate artifacts in specific detailed regions. Our experimental results demonstrate that our method significantly improves the PSNR index by approximately 5% compared to representative methods in the field. This remarkable advancement underscores the profound importance of our approach in the domains of new view synthesis and digital human reconstruction.
- 24 October 2023
- Published by MDPI AG in Electronics
- Vol. 12 (21) , 4382
Open AccessDeform2NeRF: Non-Rigid Deformation and 2D–3D Feature Fusion with Cross-Attention for Dynamic Human Reconstruction
Reconstructing dynamic human body models from multi-view videos poses a substantial challenge in the field of 3D computer vision. Currently, the Animatable NeRF method addresses this challenge by mapping observed points from the viewing space to a canonical space. However, this mapping introduces positional shifts in predicted points, resulting in artifacts, particularly in intricate areas. In this paper, we propose an innovative approach called Deform2NeRF that incorporates non-rigid deformation correction and image feature fusion modules into the Animatable NeRF framework to enhance the reconstruction of animatable human models. Firstly, we introduce a non-rigid deformation field network to address the issue of point position shift effectively. This network adeptly corrects positional discrepancies caused by non-rigid deformations. Secondly, we introduce a 2D–3D feature fusion learning module with cross-attention and integrate it with the NeRF network to mitigate artifacts in specific detailed regions. Our experimental results demonstrate that our method significantly improves the PSNR index by approximately 5% compared to representative methods in the field. This remarkable advancement underscores the profound importance of our approach in the domains of new view synthesis and digital human reconstruction.