Xiaoling Gu
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
Research Subjects
Xiaoling Gu has a total of 73 co-authors. Here are the top co-authors by number of shared publications:
- Zizhao Wu
School of Digital Media Technology, Hangzhou Dianzi University, Hangzhou, China
10 shared publications - Mohan Kankanhalli
National University of Singapore, Singapore, Singapore
6 shared publications - Yongkang Wong
National University of Singapore
5 shared publications - Jun Yu
Harbin Institute of Technology
4 shared publications - Zhenzhong Kuang
Hangzhou Dianzi University, Hangzhou, China
4 shared publications - Zhou Yu
Hangzhou Dianzi University, Hangzhou, China
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5281-5290
3D-Aware Eye Generation for Controllable Gaze Data Synthesis
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5281-5290
Open Access3D-Aware Eye Generation for Controllable Gaze Data Synthesis
- 6 August 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 203
The MI-Motion dataset and benchmark for 3D multi-person motion prediction
- 6 August 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 203
The MI-Motion dataset and benchmark for 3D multi-person motion prediction
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28  (15209210) , 4169-4180
Compositional Text-to-Image Synthesis With Training-Free Layout-Guided Diffusion
Recent text-to-image (T2I) diffusion models have made significant strides in generating high-quality images from diverse textual prompts. Despite this progress, these models often face challenges in accurately understanding and synthesizing complex prompts, primarily due to their limited compositional capabilities. In this study, we propose a novel approach for compositional T2I synthesis using layout-guided diffusion models, which do not require additional training. Specifically, we leverage the chain-of-code prompting technique of large language models to interpret textual prompts and generate object layouts with spatial coherence. To enhance the alignment between generated images and textual descriptions, we introduce two innovative layoutguided loss functions: Patch-oriented Cross-Attention (PCA) loss and Region-oriented Cross-Attention (RCA) loss. The PCA loss emphasizes high activation values for image patches that attend to all tokens in the prompt across the layout. The RCA loss enhances the average attention within the layout, thereby increasing the accuracy of generating objects and their associated attributes within specified regions. These proposed loss functions reassign cross-attention in diffusion models during the denoising process. Our comprehensive experiments consistently demonstrate the effectiveness of our approach in improving semantic alignment between generated images and a diverse range of textual prompts, while ensuring high usability as a ready-to-use plugin. Our code is available at https://github.com/gxl-groups/Compositional-T2I.
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28  (15209210) , 4169-4180
Compositional Text-to-Image Synthesis With Training-Free Layout-Guided Diffusion
Recent text-to-image (T2I) diffusion models have made significant strides in generating high-quality images from diverse textual prompts. Despite this progress, these models often face challenges in accurately understanding and synthesizing complex prompts, primarily due to their limited compositional capabilities. In this study, we propose a novel approach for compositional T2I synthesis using layout-guided diffusion models, which do not require additional training. Specifically, we leverage the chain-of-code prompting technique of large language models to interpret textual prompts and generate object layouts with spatial coherence. To enhance the alignment between generated images and textual descriptions, we introduce two innovative layoutguided loss functions: Patch-oriented Cross-Attention (PCA) loss and Region-oriented Cross-Attention (RCA) loss. The PCA loss emphasizes high activation values for image patches that attend to all tokens in the prompt across the layout. The RCA loss enhances the average attention within the layout, thereby increasing the accuracy of generating objects and their associated attributes within specified regions. These proposed loss functions reassign cross-attention in diffusion models during the denoising process. Our comprehensive experiments consistently demonstrate the effectiveness of our approach in improving semantic alignment between generated images and a diverse range of textual prompts, while ensuring high usability as a ready-to-use plugin. Our code is available at https://github.com/gxl-groups/Compositional-T2I.
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (6) , 8080-8091
TailorEdit: An Adaptive Framework for Instruction-Guided Fashion Image Editing
Fashion image editing has garnered significant attention due to its growing demand in e-commerce, social media, and virtual try-on applications. However, existing methods are typically designed for specific editing tasks in isolation, lacking a unified framework capable of handling diverse editing requirements. This work addresses this limitation from two critical perspectives. First, we construct InstructFashion, a large-scale, high-quality dataset specifically curated for instruction-guided fashion image editing. It is generated through carefully designed pipelines that cover four distinct editing tasks. Second, we propose TailorEdit, an adaptive framework for instruction-guided fashion image editing. It integrates human segmentation map-based denoising guidance, modular LoRA-based editing experts, and a dynamic expert routing mechanism to enable precise and semantically coherent modifications. Extensive quantitative and qualitative evaluations demonstrate that TailorEdit consistently outperforms state-of-the-art methods in terms of realism, coherence, and instruction adherence. Our code is available at https://github.com/EndaJude/TailorEdit.
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (6) , 8080-8091
TailorEdit: An Adaptive Framework for Instruction-Guided Fashion Image Editing
Fashion image editing has garnered significant attention due to its growing demand in e-commerce, social media, and virtual try-on applications. However, existing methods are typically designed for specific editing tasks in isolation, lacking a unified framework capable of handling diverse editing requirements. This work addresses this limitation from two critical perspectives. First, we construct InstructFashion, a large-scale, high-quality dataset specifically curated for instruction-guided fashion image editing. It is generated through carefully designed pipelines that cover four distinct editing tasks. Second, we propose TailorEdit, an adaptive framework for instruction-guided fashion image editing. It integrates human segmentation map-based denoising guidance, modular LoRA-based editing experts, and a dynamic expert routing mechanism to enable precise and semantically coherent modifications. Extensive quantitative and qualitative evaluations demonstrate that TailorEdit consistently outperforms state-of-the-art methods in terms of realism, coherence, and instruction adherence. Our code is available at https://github.com/EndaJude/TailorEdit.
- 21 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (2) , 1928-1940
InterMamba: Efficient Human-Human Interaction Generation With Adaptive Spatio-Temporal Mamba
Human-human interaction generation has garnered significant attention in motion synthesis due to its vital role in understanding humans as social beings. However, existing methods typically rely on transformer-based architectures, which often face challenges related to scalability and efficiency. To address these challenges, we propose InterMamba, a novel and efficient human–human interaction generation method built on the Mamba framework, designed to capture long-sequence dependencies effectively while enabling real-time feedback. Specifically, we introduce an adaptive spatio-temporal Mamba framework that utilizes two parallel SSM branches with an adaptive mechanism to integrate the spatial and temporal features of motion sequences. To further enhance the model's ability to capture dependencies within individual motion sequences and the interactions between different individual sequences, we develop two key modules: the self adaptive spatio-temporal Mamba module and the cross adaptive spatio-temporal Mamba module, enabling efficient feature learning. Extensive experiments demonstrate that our method achieves the state-of-the-art results on both two interaction datasets with remarkable quality and efficiency. Compared to the baseline method InterGen, our approach not only improves accuracy but also reduces the parameter size to just 66 M (36% of InterGen's), while achieving an average inference speed of 0.57 seconds, which is 46% of InterGen's execution time.
- 21 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (2) , 1928-1940
InterMamba: Efficient Human-Human Interaction Generation With Adaptive Spatio-Temporal Mamba
Human-human interaction generation has garnered significant attention in motion synthesis due to its vital role in understanding humans as social beings. However, existing methods typically rely on transformer-based architectures, which often face challenges related to scalability and efficiency. To address these challenges, we propose InterMamba, a novel and efficient human–human interaction generation method built on the Mamba framework, designed to capture long-sequence dependencies effectively while enabling real-time feedback. Specifically, we introduce an adaptive spatio-temporal Mamba framework that utilizes two parallel SSM branches with an adaptive mechanism to integrate the spatial and temporal features of motion sequences. To further enhance the model's ability to capture dependencies within individual motion sequences and the interactions between different individual sequences, we develop two key modules: the self adaptive spatio-temporal Mamba module and the cross adaptive spatio-temporal Mamba module, enabling efficient feature learning. Extensive experiments demonstrate that our method achieves the state-of-the-art results on both two interaction datasets with remarkable quality and efficiency. Compared to the baseline method InterGen, our approach not only improves accuracy but also reduces the parameter size to just 66 M (36% of InterGen's), while achieving an average inference speed of 0.57 seconds, which is 46% of InterGen's execution time.
- 17 July 2025
- Published by Springer Nature in The Visual Computer
- Vol. 41  (13) , 11195-11205
Interpretable procedural material graph generation via diffusion models from reference images
- 17 July 2025
- Published by Springer Nature in The Visual Computer
- Vol. 41  (13) , 11195-11205
Interpretable procedural material graph generation via diffusion models from reference images
- 15 July 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 182
Texture-aware 3D Gaussian Splatting for sparse view reconstructions
- 15 July 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 182
Texture-aware 3D Gaussian Splatting for sparse view reconstructions
- Open Access
InterMamba: Efficient Human-Human Interaction Generation with Adaptive Spatio-Temporal Mamba
Human-human interaction generation has garnered significant attention in motion synthesis due to its vital role in understanding humans as social beings. However, existing methods typically rely on transformer-based architectures, which often face challenges related to scalability and efficiency. To address these issues, we propose a novel, efficient human-human interaction generation method based on the Mamba framework, designed to meet the demands of effectively capturing long-sequence dependencies while providing real-time feedback. Specifically, we introduce an adaptive spatio-temporal Mamba framework that utilizes two parallel SSM branches with an adaptive mechanism to integrate the spatial and temporal features of motion sequences. To further enhance the model's ability to capture dependencies within individual motion sequences and the interactions between different individual sequences, we develop two key modules: the self-adaptive spatio-temporal Mamba module and the cross-adaptive spatio-temporal Mamba module, enabling efficient feature learning. Extensive experiments demonstrate that our method achieves state-of-the-art results on two interaction datasets with remarkable quality and efficiency. Compared to the baseline method InterGen, our approach not only improves accuracy but also requires a minimal parameter size of just 66M ,only 36% of InterGen's, while achieving an average inference speed of 0.57 seconds, which is 46% of InterGen's execution time.
Open AccessInterMamba: Efficient Human-Human Interaction Generation with Adaptive Spatio-Temporal Mamba
Human-human interaction generation has garnered significant attention in motion synthesis due to its vital role in understanding humans as social beings. However, existing methods typically rely on transformer-based architectures, which often face challenges related to scalability and efficiency. To address these issues, we propose a novel, efficient human-human interaction generation method based on the Mamba framework, designed to meet the demands of effectively capturing long-sequence dependencies while providing real-time feedback. Specifically, we introduce an adaptive spatio-temporal Mamba framework that utilizes two parallel SSM branches with an adaptive mechanism to integrate the spatial and temporal features of motion sequences. To further enhance the model's ability to capture dependencies within individual motion sequences and the interactions between different individual sequences, we develop two key modules: the self-adaptive spatio-temporal Mamba module and the cross-adaptive spatio-temporal Mamba module, enabling efficient feature learning. Extensive experiments demonstrate that our method achieves state-of-the-art results on two interaction datasets with remarkable quality and efficiency. Compared to the baseline method InterGen, our approach not only improves accuracy but also requires a minimal parameter size of just 66M ,only 36% of InterGen's, while achieving an average inference speed of 0.57 seconds, which is 46% of InterGen's execution time.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1370-1378
3D Question Answering with Scene Graph Reasoning
3DQA has gained considerable attention due to its enhanced spatial understanding capabilities compared to image-based VQA. However, existing 3DQA methods have explicitly focused on integrating text and color-coded point cloud features, thereby overlooking the rich high-level semantic relationships among objects. In this paper, we propose a novel graph-based 3DQA method termed 3DGraphQA, which leverages scene graph reasoning to enhance the ability to handle complex reasoning tasks in 3DQA and offers stronger interpretability. Specifically, our method first adaptively constructs dynamic scene graphs for the 3DQA task. Then we inject both the situation and the question inputs into the scene graph, forming the situation-graph and the question-graph, respectively. Based on the constructed graphs, we finally perform intra- and inter-graph feature propagation for efficient graph inference: intra-graph feature propagation is performed based on Graph Transformer in each graph to realize single-modal contextual interaction and high-order contextual interaction; inter-graph feature propagation is performed among graphs based on bilinear graph networks to realize the interaction between different contexts of situations and questions. Drawing on these intra- and inter-graph feature propagation, our approach is poised to better grasp the intricate semantic and spatial relationship issues among objects within the scene and their relations to the questions, thereby facilitating reasoning complex and compositional questions. We validate the effectiveness of our approach on SQA3D and ScanQA datasets, and expand the SQA3D dataset to SQA3D Pro with multi-view information, making it more suitable for our approach. Experimental results demonstrate that our 3DGraphQA outperforms existing methods.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1370-1378
Open Access3D Question Answering with Scene Graph Reasoning
3DQA has gained considerable attention due to its enhanced spatial understanding capabilities compared to image-based VQA. However, existing 3DQA methods have explicitly focused on integrating text and color-coded point cloud features, thereby overlooking the rich high-level semantic relationships among objects. In this paper, we propose a novel graph-based 3DQA method termed 3DGraphQA, which leverages scene graph reasoning to enhance the ability to handle complex reasoning tasks in 3DQA and offers stronger interpretability. Specifically, our method first adaptively constructs dynamic scene graphs for the 3DQA task. Then we inject both the situation and the question inputs into the scene graph, forming the situation-graph and the question-graph, respectively. Based on the constructed graphs, we finally perform intra- and inter-graph feature propagation for efficient graph inference: intra-graph feature propagation is performed based on Graph Transformer in each graph to realize single-modal contextual interaction and high-order contextual interaction; inter-graph feature propagation is performed among graphs based on bilinear graph networks to realize the interaction between different contexts of situations and questions. Drawing on these intra- and inter-graph feature propagation, our approach is poised to better grasp the intricate semantic and spatial relationship issues among objects within the scene and their relations to the questions, thereby facilitating reasoning complex and compositional questions. We validate the effectiveness of our approach on SQA3D and ScanQA datasets, and expand the SQA3D dataset to SQA3D Pro with multi-view information, making it more suitable for our approach. Experimental results demonstrate that our 3DGraphQA outperforms existing methods.
- 26 September 2024
- Published by Springer Nature in The Visual Computer
- Vol. 41  (6) , 3973-4000
Innovative AI techniques for photorealistic 3D clothed human reconstruction from monocular images or videos: a survey
- 26 September 2024
- Published by Springer Nature in The Visual Computer
- Vol. 41  (6) , 3973-4000
Innovative AI techniques for photorealistic 3D clothed human reconstruction from monocular images or videos: a survey