Motion magnification

By Ce Liu, Antonio Torralba, William T. Freeman, Frédo Durand, Edward H. Adelson. 2005

372 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Learning-based Video Motion Magnification (2018, neutral): “Lagrangian approach explicitly extracts the motion field (optical flow) and uses it to move the pixels directly [8].”
A Boost in Revealing Subtle Facial Expressions: A Consolidated Eulerian Framework (2019, methodology): “MAG [19], [30], [35] amplifies the intensity of motion and makes subtle motion much easier to observe.”
Automated video looping with progressive dynamism (2013, background): “…video processing operations have been explored, including animating still images [Freeman et al. 1991; Chuang et al. 2005], magnifying motion [Liu et al. 2005; Wu et al. 2012], enhancing time-lapse video [Bennett and McMillan 2007; Sunkavalli et al. 2007], manipulating time in video editing…”
Video magnification in presence of large motions (2015, methodology): “Lagrangian approaches can only magnify motion changes [7, 2], while Eulerian can magnify motion [14, 11] as well as color changes [17].”
Riesz pyramids for fast phase-based video magnification (2014, methodology): “In practice, we found that using two three-tap filters to approximate the Riesz transform gave motion magnification results that were comparable to using higher-tap approximations or the frequency domain implementation of the Riesz transform.”
Particle Video: Long-Range Motion Estimation Using Point Trajectories (2006, background): “Another alternative is to adjust the region of support for a feature to fall only on one side of the occlusion (Sawhney et al. 2001; Liu et al. 2005).”
Eulerian video magnification for revealing subtle changes in the world (2012, methodology): “Our processing can amplify small motion even though we do not track motion as in Lagrangian methods [Liu et al. 2005; Wang et al. 2006].”
Video Acceleration Magnification (2017, background): “In [16] features are extracted over the frame and these features are tracked and clustered into groups of points where the video changes are magnified.”
Beyond pixels: exploring new representations and applications for motion analysis (2009, methodology): “Motion magnification is a visual system to magnify small motions in video sequences [67].”
Phase-based video motion processing (2013, methodology): “Lagrangian approaches to motion magnification (e.g. [Liu et al. 2005]) are complementary to the Eulerian approach proposed in this paper.”