Supplementary materials - STB-VMM: Swin Transformer Based Video Motion Magnification

Reference benchmark videos showcased in STB-VMM: Swin Transformer Based Video Motion Magnification. This dataset contains the original benchmarks as well as the results obtained using STB-VMM and learning-based video motion magnification (LB-VMM) [10.48550/arXiv.1804.02684]. These videos serve as a qualitative comparison between both learning based methods' image quality. The dataset is intended to help researchers and practitioners in the field of video motion magnification to evaluate and compare the performance of different methods. The code for STB-VMM is open source and available at: https://github.com/RLado/STB-VMMSTB-VMM：基于Swin Transformer的视频运动放大（Swin Transformer Based Video Motion Magnification）中展示的基准参考视频。本数据集包含原始基准视频，以及分别使用STB-VMM与基于学习的视频运动放大（Learning-Based Video Motion Magnification，缩写LB-VMM）[10.48550/arXiv.1804.02684]得到的处理结果。这些视频可用于对STB-VMM与LB-VMM这两种基于学习的方法的图像质量开展定性对比。本数据集旨在为视频运动放大领域的研究人员与从业者提供不同方法的性能评估与对比工作提供支持。 STB-VMM的代码已开源，获取地址为：https://github.com/RLado/STB-VMM