Figure 4.

(a) Original video from [17]; and (b–e) magnification results using: Linear EVM [6], PVM [12], EVAM [17] and our algorithm, respectively. For each method, we show the spatio-temporal $Y-T$ slice of the blue line marked in a frame from corresponding video. The goal of magnification is to reveal the vibration of cat toy while not induces artifacts and blurring. As can be seen from the magnification results, EVAM [17] and our algorithm can realize this goal while the linear EVM [6] and PVM [12] fail.