Visible images have been widely used for indoor motion estimation. Thermal images, in contrast, are more challenging to be used in motion estimation since they typically have lower resolution, less texture, and more noise. In this paper, a novel dataset for evaluating the performance of multi-spectral motion estimation systems is presented. The dataset includes both multi-spectral and dense depth images with accurate ground-truth camera poses provided by a motion capture system. All the sequences are recorded from a handheld multi-spectral device, which consists of a standard visible-light camera, a long-wave infrared camera, and a depth camera. The multi-spectral images, including both color and thermal images in full sensor resolution (640 $\times$ 480), are obtained from the hardware-synchronized standard and long-wave infrared camera at 32Hz. The depth images are captured by a Microsoft Kinect2 and can have benefits for learning cross-modalities stereo matching. In addition to the sequences with bright illumination, the dataset also contains scenes with dim or varying illumination. The full dataset, including both raw data and calibration data with detailed specifications of data format, is publicly available.

中文翻译：

---

用于评估多光谱运动估计方法的数据集

可见图像已被广泛用于室内运动估计。相比之下，热图像用于运动估计更具挑战性，因为它们通常具有较低的分辨率、较少的纹理和较多的噪声。在本文中，提出了一种用于评估多光谱运动估计系统性能的新数据集。该数据集包括多光谱和密集深度图像，以及运动捕捉系统提供的准确地面实况相机姿势。所有序列均由手持式多光谱设备记录，该设备由标准可见光相机、长波红外相机和深度相机组成。多光谱图像，包括全传感器分辨率（640 $\times $ 480）的彩色和热图像，是从硬件同步的标准和 32Hz 长波红外相机中获得的。深度图像由 Microsoft Kinect2 捕获，可用于学习跨模态立体匹配。除了具有明亮照明的序列之外，数据集还包含具有昏暗或变化照明的场景。完整的数据集，包括原始数据和带有详细数据格式规范的校准数据，都是公开可用的。