Shan Gao
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
Shan Gao has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Guangqian Guo
Northwestern Polytechnical University
12 shared publications - Dian Shao
Unmanned System Research Institute, Northwestern Polytechnical University, Xi’an, China
4 shared publications Guangqian Guo
Northwestern Polytechnical University
4 shared publications- Huafeng Chen
Northwestern Polytechnical University
4 shared publications - Pengxu Wei
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
4 shared publications - Huafeng Chen
Unmanned System Research Institute, Northwestern Polytechnical University, Xian, China
3 shared publications
Latest Publications
- 5 November 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (11) , 510
Hint-Guided Point-Supervised Camouflaged Object Detection with Edge-Aware Refinement
- 5 November 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (11) , 510
Hint-Guided Point-Supervised Camouflaged Object Detection with Edge-Aware Refinement
- 10 September 2026
- Published by Springer Nature
- p. 190-208
Frequency Director: Learnable Mixture of Frequency Experts for Unified Concealed Scene Segmentation
- 10 September 2026
- Published by Springer Nature
- p. 190-208
Frequency Director: Learnable Mixture of Frequency Experts for Unified Concealed Scene Segmentation
- 11 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
TMamba: Global Channel-Location Token Interaction for Multi-Modality Image Fusion
Multi-modality image fusion aims to integrate the merits of images from different sources and render high-quality fused images. Existing CNN-based image fusion backbones are limited by biases caused by local receptive fields and static parameters during inference. Transformer-based models have global receptive fields, but to avoid the trouble caused by quadratic computational complexity, they usually use self-attention mechanisms with fixed range windows or along the channel dimension, which limits the utilization of the global receptive field. To address this problem, we propose a hybrid Transformer-Mamba structure, called TMamba. Mamba has excellent global feature extraction capabilities but lacks efficient interactions between its channels. We use the linear Transformer to capture features through token interactions between channels and use the Mamba to capture features through token interactions at different spatial locations. It allows the model to extract global features from different dimensions and optimize each other while maintaining linear complexity. We further introduce three-level interactions among branches, modalities, and TMamba structures. Branch interaction enables channel and spatial global features to be transferred between Transformer and Mamba branches. Modality interaction integrates features of different modalities. TMamba interaction integrates and strengthens features from different branches. Experiments show that our TMamba achieves excellent results in multiple fusion tasks, including infrared-visible image fusion and medical image fusion. Code with checkpoints will be provided after peer review.
- 11 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
TMamba: Global Channel-Location Token Interaction for Multi-Modality Image Fusion
Multi-modality image fusion aims to integrate the merits of images from different sources and render high-quality fused images. Existing CNN-based image fusion backbones are limited by biases caused by local receptive fields and static parameters during inference. Transformer-based models have global receptive fields, but to avoid the trouble caused by quadratic computational complexity, they usually use self-attention mechanisms with fixed range windows or along the channel dimension, which limits the utilization of the global receptive field. To address this problem, we propose a hybrid Transformer-Mamba structure, called TMamba. Mamba has excellent global feature extraction capabilities but lacks efficient interactions between its channels. We use the linear Transformer to capture features through token interactions between channels and use the Mamba to capture features through token interactions at different spatial locations. It allows the model to extract global features from different dimensions and optimize each other while maintaining linear complexity. We further introduce three-level interactions among branches, modalities, and TMamba structures. Branch interaction enables channel and spatial global features to be transferred between Transformer and Mamba branches. Modality interaction integrates features of different modalities. TMamba interaction integrates and strengthens features from different branches. Experiments show that our TMamba achieves excellent results in multiple fusion tasks, including infrared-visible image fusion and medical image fusion. Code with checkpoints will be provided after peer review.
- Open Access
Boosting Segment Anything Model to Generalize Visually Non-Salient Scenarios
Segment Anything Model (SAM), known for its remarkable zero-shot segmentation capabilities, has garnered significant attention in the community. Nevertheless, its performance is challenged when dealing with what we refer to as visually non-salient scenarios, where there is low contrast between the foreground and background. In these cases, existing methods often cannot capture accurate contours and fail to produce promising segmentation results. In this paper, we propose Visually Non-Salient SAM (VNS-SAM), aiming to enhance SAM's perception of visually non-salient scenarios while preserving its original zero-shot generalizability. We achieve this by effectively exploiting SAM's low-level features through two designs: Mask-Edge Token Interactive decoder and Non-Salient Feature Mining module. These designs help the SAM decoder gain a deeper understanding of non-salient characteristics with only marginal parameter increments and computational requirements. The additional parameters of VNS-SAM can be optimized within 4 hours, demonstrating its feasibility and practicality. In terms of data, we established VNS-SEG, a unified dataset for various VNS scenarios, with more than 35K images, in contrast to previous single-task adaptations. It is designed to make the model learn more robust VNS features and comprehensively benchmark the model's segmentation performance and generalizability on VNS scenarios. Extensive experiments across various VNS segmentation tasks demonstrate the superior performance of VNS-SAM, particularly under zero-shot settings, highlighting its potential for broad real-world applications. Codes and datasets are publicly available at https://guangqian-guo.github.io/VNS-SAM.
Open AccessBoosting Segment Anything Model to Generalize Visually Non-Salient Scenarios
Segment Anything Model (SAM), known for its remarkable zero-shot segmentation capabilities, has garnered significant attention in the community. Nevertheless, its performance is challenged when dealing with what we refer to as visually non-salient scenarios, where there is low contrast between the foreground and background. In these cases, existing methods often cannot capture accurate contours and fail to produce promising segmentation results. In this paper, we propose Visually Non-Salient SAM (VNS-SAM), aiming to enhance SAM's perception of visually non-salient scenarios while preserving its original zero-shot generalizability. We achieve this by effectively exploiting SAM's low-level features through two designs: Mask-Edge Token Interactive decoder and Non-Salient Feature Mining module. These designs help the SAM decoder gain a deeper understanding of non-salient characteristics with only marginal parameter increments and computational requirements. The additional parameters of VNS-SAM can be optimized within 4 hours, demonstrating its feasibility and practicality. In terms of data, we established VNS-SEG, a unified dataset for various VNS scenarios, with more than 35K images, in contrast to previous single-task adaptations. It is designed to make the model learn more robust VNS features and comprehensively benchmark the model's segmentation performance and generalizability on VNS scenarios. Extensive experiments across various VNS segmentation tasks demonstrate the superior performance of VNS-SAM, particularly under zero-shot settings, highlighting its potential for broad real-world applications. Codes and datasets are publicly available at https://guangqian-guo.github.io/VNS-SAM.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 8429-8442
ThermalGate-GS: Frequency-Gated Graph Splatting for Thermal Novel View Synthesis
Thermal infrared imaging is pivotal for all-weather 3D perception, yet analyzing thermal information remains a formidable challenge due to the complexity of heat conduction. Unlike visible light, heat conduction acts as a natural low-pass filter that suppresses high-frequency textural details, causing severe geometric ambiguities and "ghosting" artifacts in standard 3D reconstruction pipelines. To accurately model the inherently diffusive thermal field for high-fidelity reconstruction, we propose Frequency-Gated Graph Splatting (ThermalGate-GS), a frame work that explicitly decouples the scene into diffusive thermal distributions (low-frequency) and sharp structural boundaries (high-frequency). Within this framework, we introduce a novel Frequency-Gated Anisotropic Diffusion mechanism. Specifically, the frequency-gating module utilizes extracted high-frequency structural cues to determine spatially-adaptive gating weights. Subsequently, these weights drive an anisotropic diffusion process that dynamically regulates thermal feature propagation, pro moting smoothness on object surfaces while suppressing cross-boundary bleeding. Finally, these spectrally refined features are employed to regress 3D Gaussian attributes, substantially alleviating the ambiguity in thermal reconstruction. Extensive experiments demonstrate that ThermalGate-GS achieves state-of-the-art performance, with a notable 7.94 dB PSNR improvement on the ThermoScenes benchmark over prior physics-inspired baselines.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 8429-8442
ThermalGate-GS: Frequency-Gated Graph Splatting for Thermal Novel View Synthesis
Thermal infrared imaging is pivotal for all-weather 3D perception, yet analyzing thermal information remains a formidable challenge due to the complexity of heat conduction. Unlike visible light, heat conduction acts as a natural low-pass filter that suppresses high-frequency textural details, causing severe geometric ambiguities and "ghosting" artifacts in standard 3D reconstruction pipelines. To accurately model the inherently diffusive thermal field for high-fidelity reconstruction, we propose Frequency-Gated Graph Splatting (ThermalGate-GS), a frame work that explicitly decouples the scene into diffusive thermal distributions (low-frequency) and sharp structural boundaries (high-frequency). Within this framework, we introduce a novel Frequency-Gated Anisotropic Diffusion mechanism. Specifically, the frequency-gating module utilizes extracted high-frequency structural cues to determine spatially-adaptive gating weights. Subsequently, these weights drive an anisotropic diffusion process that dynamically regulates thermal feature propagation, pro moting smoothness on object surfaces while suppressing cross-boundary bleeding. Finally, these spectrally refined features are employed to regress 3D Gaussian attributes, substantially alleviating the ambiguity in thermal reconstruction. Extensive experiments demonstrate that ThermalGate-GS achieves state-of-the-art performance, with a notable 7.94 dB PSNR improvement on the ThermoScenes benchmark over prior physics-inspired baselines.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 1143-1157
Boosting Segment Anything Model to Generalize Visually Non-Salient Scenarios
Segment Anything Model (SAM), known for its remarkable zero-shot segmentation capabilities, has garnered significant attention in the community. Nevertheless, its performance is challenged when dealing with what we refer to as visually non-salient scenarios, where there is low contrast between the foreground and background. In these cases, existing methods often cannot capture accurate contours and fail to produce promising segmentation results. In this paper, we propose Visually Non-Salient SAM (VNS-SAM), aiming to enhance SAM's perception of visually non-salient scenarios while preserving its original zero-shot generalizability. We achieve this by effectively exploiting SAM's low-level features through two designs: Mask-Edge Token Interactive decoder and Non-Salient Feature Mining module. These designs help the SAM decoder gain a deeper understanding of non-salient characteristics with only marginal parameter increments and computational requirements. The additional parameters of VNS-SAM can be optimized within 4 hours, demonstrating its feasibility and practicality. In terms of data, we established VNS-SEG, a unified dataset for various VNS scenarios, with more than 35K images, in contrast to previous single-task adaptations. It is designed to make the model learn more robust VNS features and comprehensively benchmark the model's segmentation performance and generalizability on VNS scenarios. Extensive experiments across various VNS segmentation tasks demonstrate the superior performance of VNS-SAM, particularly under zero-shot settings, highlighting its potential for broad real-world applications. Codes and datasets will be publicly available at https://guangqian-guo.github.io/VNS-SAM/.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 1143-1157
Boosting Segment Anything Model to Generalize Visually Non-Salient Scenarios
Segment Anything Model (SAM), known for its remarkable zero-shot segmentation capabilities, has garnered significant attention in the community. Nevertheless, its performance is challenged when dealing with what we refer to as visually non-salient scenarios, where there is low contrast between the foreground and background. In these cases, existing methods often cannot capture accurate contours and fail to produce promising segmentation results. In this paper, we propose Visually Non-Salient SAM (VNS-SAM), aiming to enhance SAM's perception of visually non-salient scenarios while preserving its original zero-shot generalizability. We achieve this by effectively exploiting SAM's low-level features through two designs: Mask-Edge Token Interactive decoder and Non-Salient Feature Mining module. These designs help the SAM decoder gain a deeper understanding of non-salient characteristics with only marginal parameter increments and computational requirements. The additional parameters of VNS-SAM can be optimized within 4 hours, demonstrating its feasibility and practicality. In terms of data, we established VNS-SEG, a unified dataset for various VNS scenarios, with more than 35K images, in contrast to previous single-task adaptations. It is designed to make the model learn more robust VNS features and comprehensively benchmark the model's segmentation performance and generalizability on VNS scenarios. Extensive experiments across various VNS segmentation tasks demonstrate the superior performance of VNS-SAM, particularly under zero-shot settings, highlighting its potential for broad real-world applications. Codes and datasets will be publicly available at https://guangqian-guo.github.io/VNS-SAM/.
- Open Access
ReLayout: Integrating Relation Reasoning for Content-aware Layout Generation with Multi-modal Large Language Models
Content-aware layout aims to arrange design elements appropriately on a given canvas to convey information effectively. Recently, the trend for this task has been to leverage large language models (LLMs) to generate layouts automatically, achieving remarkable performance. However, existing LLM-based methods fail to adequately interpret spatial relationships among visual themes and design elements, leading to structural and diverse problems in layout generation. To address this issue, we introduce ReLayout, a novel method that leverages relation-CoT to generate more reasonable and aesthetically coherent layouts by fundamentally originating from design concepts. Specifically, we enhance layout annotations by introducing explicit relation definitions, such as region, salient, and margin between elements, with the goal of decomposing the layout into smaller, structured, and recursive layouts, thereby enabling the generation of more structured layouts. Furthermore, based on these defined relationships, we introduce a layout prototype rebalance sampler, which defines layout prototype features across three dimensions and quantifies distinct layout styles. This sampler addresses uniformity issues in generation that arise from data bias in the prototype distribution balance process. Extensive experimental results verify that ReLayout outperforms baselines and can generate structural and diverse layouts that are more aligned with human aesthetics and more explainable.
Open AccessReLayout: Integrating Relation Reasoning for Content-aware Layout Generation with Multi-modal Large Language Models
Content-aware layout aims to arrange design elements appropriately on a given canvas to convey information effectively. Recently, the trend for this task has been to leverage large language models (LLMs) to generate layouts automatically, achieving remarkable performance. However, existing LLM-based methods fail to adequately interpret spatial relationships among visual themes and design elements, leading to structural and diverse problems in layout generation. To address this issue, we introduce ReLayout, a novel method that leverages relation-CoT to generate more reasonable and aesthetically coherent layouts by fundamentally originating from design concepts. Specifically, we enhance layout annotations by introducing explicit relation definitions, such as region, salient, and margin between elements, with the goal of decomposing the layout into smaller, structured, and recursive layouts, thereby enabling the generation of more structured layouts. Furthermore, based on these defined relationships, we introduce a layout prototype rebalance sampler, which defines layout prototype features across three dimensions and quantifies distinct layout styles. This sampler addresses uniformity issues in generation that arise from data bias in the prototype distribution balance process. Extensive experimental results verify that ReLayout outperforms baselines and can generate structural and diverse layouts that are more aligned with human aesthetics and more explainable.
- 11 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (5) , 4635-4647
SAM-COD+: SAM-Guided Unified Framework for Weakly-Supervised Camouflaged Object Detection
Most Camouflaged Object Detection (COD) methods heavily rely on mask annotations, which are time-consuming and labor-intensive to acquire. Existing weakly-supervised COD approaches exhibit significantly inferior performance compared to fully-supervised methods and struggle to simultaneously support all the existing types of camouflaged object labels, including scribbles, bounding boxes, and points. Even for Segment Anything Model (SAM), it is still problematic to handle the weakly-supervised COD and it typically encounters challenges of prompt compatibility of the scribble labels, extreme response, semantically erroneous response, and unstable feature representations, producing unsatisfactory results in camouflaged scenes. To mitigate these issues, we propose a unified COD framework in this paper, termed SAM-COD, which is capable of supporting arbitrary weakly-supervised labels. Our SAM-COD employs a prompt adapter to handle scribbles as prompts based on SAM. Meanwhile, we introduce response filter and semantic matcher modules to improve the quality of the masks obtained by SAM under COD prompts. To alleviate the negative impacts of inaccurate mask predictions, a new strategy of prompt-adaptive knowledge distillation is utilized to ensure a reliable feature representation. To validate the effectiveness of our approach, we have conducted extensive empirical experiments on three mainstream COD benchmarks. The results demonstrate the superiority of our method against state-of-the-art weakly-supervised and even fully-supervised methods. Our source codes and trained models will be publicly released.
- 11 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (5) , 4635-4647
SAM-COD+: SAM-Guided Unified Framework for Weakly-Supervised Camouflaged Object Detection
Most Camouflaged Object Detection (COD) methods heavily rely on mask annotations, which are time-consuming and labor-intensive to acquire. Existing weakly-supervised COD approaches exhibit significantly inferior performance compared to fully-supervised methods and struggle to simultaneously support all the existing types of camouflaged object labels, including scribbles, bounding boxes, and points. Even for Segment Anything Model (SAM), it is still problematic to handle the weakly-supervised COD and it typically encounters challenges of prompt compatibility of the scribble labels, extreme response, semantically erroneous response, and unstable feature representations, producing unsatisfactory results in camouflaged scenes. To mitigate these issues, we propose a unified COD framework in this paper, termed SAM-COD, which is capable of supporting arbitrary weakly-supervised labels. Our SAM-COD employs a prompt adapter to handle scribbles as prompts based on SAM. Meanwhile, we introduce response filter and semantic matcher modules to improve the quality of the masks obtained by SAM under COD prompts. To alleviate the negative impacts of inaccurate mask predictions, a new strategy of prompt-adaptive knowledge distillation is utilized to ensure a reliable feature representation. To validate the effectiveness of our approach, we have conducted extensive empirical experiments on three mainstream COD benchmarks. The results demonstrate the superiority of our method against state-of-the-art weakly-supervised and even fully-supervised methods. Our source codes and trained models will be publicly released.
- 30 September 2024
- Published by Springer Nature
- p. 332-348
Just a Hint: Point-Supervised Camouflaged Object Detection
- 30 September 2024
- Published by Springer Nature
- p. 332-348
Just a Hint: Point-Supervised Camouflaged Object Detection
- 30 September 2024
- Published by Springer Nature
- p. 315-331
SAM-COD: SAM-Guided Unified Framework for Weakly-Supervised Camouflaged Object Detection
- 30 September 2024
- Published by Springer Nature
- p. 315-331
SAM-COD: SAM-Guided Unified Framework for Weakly-Supervised Camouflaged Object Detection