DYDongsheng Yang

Dongsheng Yang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dongsheng Yang has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • TMamba: Global Channel-Location Token Interaction for Multi-Modality Image Fusion

    by Chenguang Zhu, Huafeng Chen, Guangqian Guo, Dongsheng Yang, Kai Zhang, Shan Gao

    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

    HOGnet-driven Siamese architecture for quantifying complexity of infrared countermeasure scenarios

    by Feng Xie, Siqi Chen, Dongsheng Yang, Yao Yang, Tao Wang

  • ThermalGate-GS: Frequency-Gated Graph Splatting for Thermal Novel View Synthesis

    by Yaoxing Wang, Wenkang Chen, Yuheng Li, Guangqian Guo, Chaowei Wang, Yan Di, Dongsheng Yang, Kai Zhang, Shan Gao

    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.

  • Complexity Evaluation of Aerial Infrared Countermeasure Scenes

    by Feng Xie, Minzhou Dong, Xiaotian Wang, Dongsheng Yang, Jie Yan

    Unmanned aerial vehicles (UAVs) are being increasingly deployed in modern battlefields owing to their low cost, stealth capabilities, and challenging interception. The recent Russian-Ukrainian conflict has further highlighted the widespread and far-reaching impact of UAVs. Therefore, the offensive and defensive countermeasures for UAVs have attracted considerable research attention. With the development of various optoelectronic interference methods, the complexity of the battlefield environments of UAVs has increased, posing significant challenges for infrared (IR) target identification and tracking. This study explored methodologies for evaluating IR counter-measure scenes involving UAVs. A detailed survey of the extensive literature on scene evaluation was conducted for the quantitative assessment of factors