Shengling Geng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shengling Geng has a total of 58 co-authors. Here are the top co-authors by number of shared publications:
- Dan Zhang
Department of Mechanical Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China
7 shared publications Fubo Wang
4 shared publications- Yongming Li
Shaanxi Normal University
4 shared publications Zeyu Jia
4 shared publications- Banghe Han
Xidian University
3 shared publications Mingcong Dang
School of Computer, Qinghai Normal University, Hutai, Xining, China
3 shared publications
Latest Publications
- 1 October 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
GLAF: Test-time adaptive global–local knowledge fusion for retrieval-augmented image generation
- 1 October 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
GLAF: Test-time adaptive global–local knowledge fusion for retrieval-augmented image generation
- Open Access
- 21 August 2026
- Published by Springer Nature in npj Heritage Science
A structure-aware diffusion framework for generalizable mural restoration
- 21 August 2026
- Published by Springer Nature in npj Heritage Science
Open AccessA structure-aware diffusion framework for generalizable mural restoration
- Open Access
- 1 August 2026
- Published by Springer Nature in npj Heritage Science
A sketch-and-text guided diffusion framework for Tibetan painting generation for digital heritage preservation
- 1 August 2026
- Published by Springer Nature in npj Heritage Science
Open AccessA sketch-and-text guided diffusion framework for Tibetan painting generation for digital heritage preservation
- 4 June 2026
- Published by Elsevier in Neural Networks
- Vol. 204, 109201
SA-RAG: Structured and adaptive retrieval-augmented generation for multi-hop question answering
- 4 June 2026
- Published by Elsevier in Neural Networks
- Vol. 204, 109201
SA-RAG: Structured and adaptive retrieval-augmented generation for multi-hop question answering
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 34423-34440
DGCANet: Dynamic Gating Cross-Attention Network With Frequency-Domain Spectral Enhancement for HSI–LiDAR Classification
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 34423-34440
Open AccessDGCANet: Dynamic Gating Cross-Attention Network With Frequency-Domain Spectral Enhancement for HSI–LiDAR Classification
- 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/.
- Open Access
- 30 September 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (19) , 10573
Research on High-Resolution Image Harmonization Method Based on Multi-Scale and Global Feature Guidance
During the image compositing process, there may be inconsistencies in tone and illumination between the foreground and background, leading to poor visual quality and low realism in the composite images. To address these issues, image harmonization techniques can be employed. This paper proposes an image harmonization method based on multi-scale and global feature guidance (MSGF). In general, images captured in different scenes may exhibit inconsistencies in lighting after composition. The goal of image harmonization is to adjust the foreground illumination to match that of the background. Traditional methods often attempt to blend pixels directly, which can result in unrealistic outcomes. The proposed approach combines multi-scale feature extraction with global feature guidance, forming the MSGF framework. The experiment was conducted on the iHarmony4 dataset. Comparative experiments showed that MSGF achieved the best performance on three subset indicators, including HCOCO. Ablation studies demonstrated the effectiveness of the proposed module. Efficiency evaluation results indicated that it took 0.01s and had 20.9 million parameters, outperforming comparative methods and effectively achieving high-quality image harmonization.
- 30 September 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (19) , 10573
Open AccessResearch on High-Resolution Image Harmonization Method Based on Multi-Scale and Global Feature Guidance
During the image compositing process, there may be inconsistencies in tone and illumination between the foreground and background, leading to poor visual quality and low realism in the composite images. To address these issues, image harmonization techniques can be employed. This paper proposes an image harmonization method based on multi-scale and global feature guidance (MSGF). In general, images captured in different scenes may exhibit inconsistencies in lighting after composition. The goal of image harmonization is to adjust the foreground illumination to match that of the background. Traditional methods often attempt to blend pixels directly, which can result in unrealistic outcomes. The proposed approach combines multi-scale feature extraction with global feature guidance, forming the MSGF framework. The experiment was conducted on the iHarmony4 dataset. Comparative experiments showed that MSGF achieved the best performance on three subset indicators, including HCOCO. Ablation studies demonstrated the effectiveness of the proposed module. Efficiency evaluation results indicated that it took 0.01s and had 20.9 million parameters, outperforming comparative methods and effectively achieving high-quality image harmonization.
- Open Access
- 16 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-19
Diffusion probabilistic model for Tibetan painted sketch extraction
During the process of Tibetan painting, the same sketch can be used to create different types of artwork. However, for each type, the artist must meticulously redraw an identical sketch. Crafting a complex sketch demands considerable time and effort from the artist, making the extraction of these sketchs crucial. Given the intricate colors and line structures of Tibetan paintings, existing learning-based methods for extracting sketchs often fail to accurately and clearly capture these elements. With the successful application of Diffusion Probabilistic Models (DPM), we propose a method for extracting lsketchs of Tibetan paintings based on DPM—DiffusionSketch. By introducing DPM, DiffusionSketch simultaneously captures coarse-grained global context and fine-grained local context features in two stages. We propose a corresponding adaptive wavelet filter to adjust latent features of specific frequencies and integrate the features extracted from both stages through a Feature Fusion Module (FFM). Moreover, to minimize errors and distortions in the generated sketchs, the fused output features are processed by a Generative Adversarial Network (GAN) to predict the final effect of the Tibetan painting sketchs. Through all the above technical designs, DiffusionSketch can generate clear and concise sketch of Tibetan paintings with minimal resource consumption. In our HeHuang Tibetan Painting (HHTP) dataset, the sketchs extracted by DiffusionSketch are less noisy, have clearer lines, and closely resemble the sketchs created by real Tibetan painting artists compared to existing sketch extraction methods. The sketchs extracted by our method rank first, with an average ranking of 1.137 among the results extracted by 36 different methods. On the HHTP dataset, our method outperforms the second-ranked method by 57.12 % in subjective evaluation and by 18.30 % in objective evaluation criteria. Code: https://github.com/HeHuangAI/DiffusionSketch.
- 16 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-19
Open AccessDiffusion probabilistic model for Tibetan painted sketch extraction
During the process of Tibetan painting, the same sketch can be used to create different types of artwork. However, for each type, the artist must meticulously redraw an identical sketch. Crafting a complex sketch demands considerable time and effort from the artist, making the extraction of these sketchs crucial. Given the intricate colors and line structures of Tibetan paintings, existing learning-based methods for extracting sketchs often fail to accurately and clearly capture these elements. With the successful application of Diffusion Probabilistic Models (DPM), we propose a method for extracting lsketchs of Tibetan paintings based on DPM—DiffusionSketch. By introducing DPM, DiffusionSketch simultaneously captures coarse-grained global context and fine-grained local context features in two stages. We propose a corresponding adaptive wavelet filter to adjust latent features of specific frequencies and integrate the features extracted from both stages through a Feature Fusion Module (FFM). Moreover, to minimize errors and distortions in the generated sketchs, the fused output features are processed by a Generative Adversarial Network (GAN) to predict the final effect of the Tibetan painting sketchs. Through all the above technical designs, DiffusionSketch can generate clear and concise sketch of Tibetan paintings with minimal resource consumption. In our HeHuang Tibetan Painting (HHTP) dataset, the sketchs extracted by DiffusionSketch are less noisy, have clearer lines, and closely resemble the sketchs created by real Tibetan painting artists compared to existing sketch extraction methods. The sketchs extracted by our method rank first, with an average ranking of 1.137 among the results extracted by 36 different methods. On the HHTP dataset, our method outperforms the second-ranked method by 57.12 % in subjective evaluation and by 18.30 % in objective evaluation criteria. Code: https://github.com/HeHuangAI/DiffusionSketch.
- Open Access
- 20 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 101-106
The Research on Green Screen Video Segmentation Based on Multi-scale Deep Learning Techniques
- 20 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 101-106
Open AccessThe Research on Green Screen Video Segmentation Based on Multi-scale Deep Learning Techniques
- Open Access
Fuzzy Computation Tree Temporal Logic with Quality Constraints and Its Model Checking
The encapsulation of particular quality functions and predicates within temporal logic formulas markedly enhances the representation of detailed temporal characteristics within a system. During our preliminary investigations, we innovatively combined quality constraint functions and predicates with Possibility Linear Temporal Logic (PoLTL), yielding the conception of Fuzzy Linear Temporal Logic with Quality Constraints (QFLTL). This amalgamation results in a significant elevation of QFLTL’s expressivity relative to PoLTL, ensuring the preservation of informational integrity whilst achieving a synchronized, yet selectively inclined, and exact consolidation of path reachability specifics alongside property satisfaction evaluations. This treatise represents a significant contribution to the field by integrating quality constraint functions and predicates into Possibility Computation Tree Temporal Logic (PoCTL), thus giving rise to Fuzzy Computation Tree Temporal Logic with Quality Constraints (QFCTL). We provide a comprehensive definition of QFCTL’s syntax, conduct an in-depth analysis of its logical characteristics, outline a precise model checking algorithm for QFCTL, and perform a meticulous complexity assessment of said algorithm. It is illustrated by examples that PoCTL is a proper subset of QFCTL, and QFCTL has stronger expressive power than PoCTL and can characterize more refined temporal properties of the system. An in-depth exploration of the logical characteristics of QFCTL was carried out, showing its unique logical characteristics that are distinct from other temporal logic systems under the influence of quality constraints. In particular, the introduction of characteristic predicates effectively classifies the satisfaction of temporal formulas, making the logical framework of QFCTL more complete compared to the existing probabilistic temporal logic. Moreover, by enriching QFCTL with a quantitative characteristic predicate operator, we innovate, culminating in the development of an enhanced Fuzzy Computation Tree Temporal Logic with Quality Constraints (QFCTL*). The logical characteristics of QFCTL* are explored in detail. It is shown that with the support of quantitative feature predicates, QFCTL* can divide the satisfaction of temporal formulas more delicately than QFCTL. The decision theorems for the semantics of QFCTL* formulas containing quantitative feature predicates are given, and the decidability of QFCTL* is strictly proved. Through the bounded-depth search of GPKS, a model-checking algorithm of QFCTL* on GPKS is presented. The correctness of the algorithm is proved, and the complexity of the algorithm is analyzed. In order to prove the practical applications and strong expressive capabilities of QFCTL and QFCTL*, we present a model-checking example as empirical evidence for the effectiveness of the proposed model-checking algorithms. Through this example, we verify that, compared with the existing PoCTL, QFCTL and QFCTL* can avoid the loss of system path reachability information or system property satisfaction information, ensure the synchronization of the two types of information, and fuse these two types of information according to weight preferences. QFCTL and QFCTL* can also synthesize temporal formulas that characterize the subproperties of the system according to weight preferences. These application examples also verify that the QFCTL and QFCTL* model-checking algorithms proposed in this article are automatic and effective.
Open AccessFuzzy Computation Tree Temporal Logic with Quality Constraints and Its Model Checking
The encapsulation of particular quality functions and predicates within temporal logic formulas markedly enhances the representation of detailed temporal characteristics within a system. During our preliminary investigations, we innovatively combined quality constraint functions and predicates with Possibility Linear Temporal Logic (PoLTL), yielding the conception of Fuzzy Linear Temporal Logic with Quality Constraints (QFLTL). This amalgamation results in a significant elevation of QFLTL’s expressivity relative to PoLTL, ensuring the preservation of informational integrity whilst achieving a synchronized, yet selectively inclined, and exact consolidation of path reachability specifics alongside property satisfaction evaluations. This treatise represents a significant contribution to the field by integrating quality constraint functions and predicates into Possibility Computation Tree Temporal Logic (PoCTL), thus giving rise to Fuzzy Computation Tree Temporal Logic with Quality Constraints (QFCTL). We provide a comprehensive definition of QFCTL’s syntax, conduct an in-depth analysis of its logical characteristics, outline a precise model checking algorithm for QFCTL, and perform a meticulous complexity assessment of said algorithm. It is illustrated by examples that PoCTL is a proper subset of QFCTL, and QFCTL has stronger expressive power than PoCTL and can characterize more refined temporal properties of the system. An in-depth exploration of the logical characteristics of QFCTL was carried out, showing its unique logical characteristics that are distinct from other temporal logic systems under the influence of quality constraints. In particular, the introduction of characteristic predicates effectively classifies the satisfaction of temporal formulas, making the logical framework of QFCTL more complete compared to the existing probabilistic temporal logic. Moreover, by enriching QFCTL with a quantitative characteristic predicate operator, we innovate, culminating in the development of an enhanced Fuzzy Computation Tree Temporal Logic with Quality Constraints (QFCTL*). The logical characteristics of QFCTL* are explored in detail. It is shown that with the support of quantitative feature predicates, QFCTL* can divide the satisfaction of temporal formulas more delicately than QFCTL. The decision theorems for the semantics of QFCTL* formulas containing quantitative feature predicates are given, and the decidability of QFCTL* is strictly proved. Through the bounded-depth search of GPKS, a model-checking algorithm of QFCTL* on GPKS is presented. The correctness of the algorithm is proved, and the complexity of the algorithm is analyzed. In order to prove the practical applications and strong expressive capabilities of QFCTL and QFCTL*, we present a model-checking example as empirical evidence for the effectiveness of the proposed model-checking algorithms. Through this example, we verify that, compared with the existing PoCTL, QFCTL and QFCTL* can avoid the loss of system path reachability information or system property satisfaction information, ensure the synchronization of the two types of information, and fuse these two types of information according to weight preferences. QFCTL and QFCTL* can also synthesize temporal formulas that characterize the subproperties of the system according to weight preferences. These application examples also verify that the QFCTL and QFCTL* model-checking algorithms proposed in this article are automatic and effective.