STB-VMM: Swin Transformer based Video Motion Magnification

ViMag: A Visual Vibration Analysis Toolbox

“…This work is based on the method developed by Lado-Roigé et al (2022) for vibration-based damage detection and on the Swin Transformer Based Video Motion Magnification (STB-VMM) method (Lado-Roigé & Pérez, 2023), which improves on the previous motion magnification backend (Oh et al, 2018) in terms of image quality.…”

“…Video motion magnification was first developed by C. Liu et al (2005) and opened a new range of possibilities for research, however, this first approach produced numerous visual artifacts on top of being computationally expensive. Years later,further developments by Wu et al (2012) introduced a novel Eulerian approach to magnification that produced much cleaner results with less computational cost, paving the way for newer and more refined algorithms that produced increasingly better results such as (Wadhwa et al, 2014), (Oh et al, 2018) or (Lado-Roigé & Pérez, 2023).…”