用AI自动校准高光谱图像，告别物理标定的繁琐
Automatic Spectral Calibration of Hyperspectral Images:Method, Dataset and Benchmark
- 基于学习方法实现无需物理参考的自动校准
- 构建765对高质量数据集，扩展至7650对提升泛化性
- 在低光条件下表现更优，适合遥感与工业检测场景
高光谱图像（HSI）在空间和波长域上密集采样，比RGB图像更具区分性。传统校准依赖物理参考，存在手动操作、遮挡和相机移动受限等问题。为此，本文提出一种基于学习的自动校准方法，构建了包含765对高质量HSI的大型数据集，覆盖多样自然场景与光照条件；并通过结合10种实测光照，扩展至7650对。提出光谱照明变换器（SIT）与光照注意力模块，大量基准测试表明其达到当前最优性能。结果还显示低光照条件更具挑战性。代码与数据集已开源：https://github.com/duranze/Automatic-spectral-calibration-of-HSI。
原文摘要 · Abstract (English)
Hyperspectral image (HSI) densely samples the world in both the space and frequency domain and therefore is more distinctive than RGB images. Usually, HSI needs to be calibrated to minimize the impact of various illumination conditions. The traditional way to calibrate HSI utilizes a physical reference, which involves manual operations, occlusions, and/or limits camera mobility. These limitations inspire this paper to automatically calibrate HSIs using a learning-based method. Towards this goal, a large-scale HSI calibration dataset is created, which has 765 high-quality HSI pairs covering diversified natural scenes and illuminations. The dataset is further expanded to 7650 pairs by combining with 10 different physically measured illuminations. A spectral illumination transformer (SIT) together with an illumination attention module is proposed. Extensive benchmarks demonstrate the SoTA performance of the proposed SIT. The benchmarks also indicate that low-light conditions are more challenging than normal conditions. The dataset and codes are available online:https://github.com/duranze/Automatic-spectral-calibration-of-HSI
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。