用双增强机制提升夜间无人机追踪效果，兼顾速度与内存效率。
MambaTrack: Exploiting Dual-Enhancement for Night UAV Tracking
- 基于Mamba架构设计低光增强模块，恢复图像细节并提升整体亮度。
- 引入跨模态Mamba网络，实现视觉与语言信息的高效交互学习。
- 在夜间跟踪任务中速度比CiteTracker快2.8倍，显存占用减少50.2%。
夜间无人机（UAV）追踪受光照不足严重制约，此前针对白天优化的方法在低光环境下表现不佳，限制了无人机应用。为此，我们提出一种高效的Mamba基追踪器，结合双重增强技术以提升夜间无人机追踪性能。基于Mamba的低光增强模块配备光照估测器与损伤修复器，可在保留图像细节与结构的前提下实现全局图像增强。此外，我们进一步设计跨模态Mamba网络，实现视觉与语言模态间的高效交互学习。大量实验表明，所提方法不仅达到先进性能，且在计算与内存效率上显著提升：例如，相比CiteTracker，本方法提速2.8倍，显存降低50.2%。代码已开源于：https://github.com/983632847/Awesome-Multimodal-Object-Tracking。
原文摘要 · Abstract (English)
Night unmanned aerial vehicle (UAV) tracking is impeded by the challenges of poor illumination, with previous daylight-optimized methods demonstrating suboptimal performance in low-light conditions, limiting the utility of UAV applications. To this end, we propose an efficient mamba-based tracker, leveraging dual enhancement techniques to boost night UAV tracking. The mamba-based low-light enhancer, equipped with an illumination estimator and a damage restorer, achieves global image enhancement while preserving the details and structure of low-light images. Additionally, we advance a cross-modal mamba network to achieve efficient interactive learning between vision and language modalities. Extensive experiments showcase that our method achieves advanced performance and exhibits significantly improved computation and memory efficiency. For instance, our method is 2.8$\times$ faster than CiteTracker and reduces 50.2$\%$ GPU memory. Our codes are available at \url{https://github.com/983632847/Awesome-Multimodal-Object-Tracking}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。