实时热成像立体匹配,夜间无人机与机器人导航新方案
ThermoStereoRT: Thermal Stereo Matching in Real Time via Knowledge Distillation and Attention-based Refinement
- 轻量骨干网络+多尺度注意力构建成本体积,快速生成初始视差图
- 通道与空间注意力模块提升视差图精度,在多个数据集上达到领先性能
- 知识蒸馏缓解热成像标注稀疏问题,保持实时性且不增加计算开销
我们提出ThermoStereoRT,一种用于全天候环境的实时热成像立体匹配方法,从两幅校正后的热成像立体图像中恢复视差,适用于夜间无人机监控或床下清洁机器人等场景。该方法采用轻量但强大的主干网络,从热成像构建3D代价体,并利用多尺度注意力机制生成初始视差图。为精炼视差图,设计了一种新型通道与空间注意力模块。针对热成像中地面真值数据稀疏的问题,采用知识蒸馏提升性能,同时不增加计算开销。在多个数据集上的全面评估表明,ThermoStereoRT兼具实时能力与鲁棒精度,是复杂环境下实际部署的有前景解决方案。代码将开源于https://github.com/SJTU-ViSYS-team/ThermoStereoRT
原文摘要 · Abstract (English)
We introduce ThermoStereoRT, a real-time thermal stereo matching method designed for all-weather conditions that recovers disparity from two rectified thermal stereo images, envisioning applications such as night-time drone surveillance or under-bed cleaning robots. Leveraging a lightweight yet powerful backbone, ThermoStereoRT constructs a 3D cost volume from thermal images and employs multi-scale attention mechanisms to produce an initial disparity map. To refine this map, we design a novel channel and spatial attention module. Addressing the challenge of sparse ground truth data in thermal imagery, we utilize knowledge distillation to boost performance without increasing computational demands. Comprehensive evaluations on multiple datasets demonstrate that ThermoStereoRT delivers both real-time capacity and robust accuracy, making it a promising solution for real-world deployment in various challenging environments. Our code will be released on https://github.com/SJTU-ViSYS-team/ThermoStereoRT
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。