提升自动驾驶中RGB转热成像的多样性，让生成图像更真实多样。
Increasing the Diversity in RGB-to-Thermal Image Translation for Automotive Applications
- 采用组件感知的自适应归一化，实现多模态图像风格分区域适配。
- 生成热图像在视觉上更真实，多样性显著优于传统一对一映射。
- 适合需要高逼真度仿真数据的自动驾驶感知系统研发人员。
先进驾驶辅助系统（ADAS）中的热成像技术在低光照和恶劣天气条件下比传统RGB摄像头具备更优的感知能力。然而，该领域研究受限于数据集稀缺及驾驶模拟器表征不足。RGB到热成像的图像转换可提供解决方案，但现有方法多采用一对一映射。本文提出一种一对多的多模态转换框架，引入组件感知自适应实例归一化（CoAdaIN）。与全局应用风格的原始AdaIN不同，CoAdaIN对图像不同组件分别适配风格。实验表明，该方法生成的热成像更加真实且多样化。本论文为2024年IEEE传感器会议收录论文。
原文摘要 · Abstract (English)
Thermal imaging in Advanced Driver Assistance Systems (ADAS) improves road safety with superior perception in low-light and harsh weather conditions compared to traditional RGB cameras. However, research in this area faces challenges due to limited dataset availability and poor representation in driving simulators. RGB-to-thermal image translation offers a potential solution, but existing methods focus on one-to-one mappings. We propose a one-to-many mapping using a multi-modal translation framework enhanced with our Component-aware Adaptive Instance Normalization (CoAdaIN). Unlike the original AdaIN, which applies styles globally, CoAdaIN adapts styles to different image components individually. The result, as we show, is more realistic and diverse thermal image translations. This is the accepted author manuscript of the paper published in IEEE Sensors Conference 2024. The final published version is available at 10.1109/SENSORS60989.2024.10785056.
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。