Related papers: Learning-based Video Motion Magnification
Video motion magnification is a technique to capture and amplify subtle motion in a video that is invisible to the naked eye. The deep learning-based prior work successfully demonstrates the modelling of the motion magnification problem…
Video motion magnification amplifies invisible small motions to be perceptible, which provides humans with a spatially dense and holistic understanding of small motions in the scene of interest. This is based on the premise that magnifying…
We introduce a novel self-supervised learning approach to learn representations of videos that are responsive to changes in the motion dynamics. Our representations can be learned from data without human annotation and provide a substantial…
This paper presents a simple, self-supervised method for magnifying subtle motions in video: given an input video and a magnification factor, we manipulate the video such that its new optical flow is scaled by the desired amount. To train…
The ability to amplify or reduce subtle image changes over time is useful in contexts such as video editing, medical video analysis, product quality control and sports. In these contexts there is often large motion present which severely…
The goal of video motion magnification techniques is to magnify small motions in a video to reveal previously invisible or unseen movement. Its uses extend from bio-medical applications and deepfake detection to structural modal analysis…
Motion magnification helps us visualize subtle, imperceptible motion. However, prior methods only work for 2D videos captured with a fixed camera. We present a 3D motion magnification method that can magnify subtle motions from scenes…
Robot learning of manipulation skills is hindered by the scarcity of diverse, unbiased datasets. While curated datasets can help, challenges remain in generalizability and real-world transfer. Meanwhile, large-scale "in-the-wild" video…
This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation.…
Unsupervised face animation aims to generate a human face video based on the appearance of a source image, mimicking the motion from a driving video. Existing methods typically adopted a prior-based motion model (e.g., the local affine…
Humans are continuously exposed to a stream of visual data with a natural temporal structure. However, most successful computer vision algorithms work at image level, completely discarding the precious information carried by motion. In this…
Many important physical phenomena involve subtle signals that are difficult to observe with the unaided eye, yet visualizing them can be very informative. Current motion magnification techniques can reveal these small temporal variations in…
Motion, measured via optical flow, provides a powerful cue to discover and learn objects in images and videos. However, compared to using appearance, it has some blind spots, such as the fact that objects become invisible if they do not…
How can we tell whether a video has been sped up or slowed down? How can we generate videos at different speeds? Although videos have been central to modern computer vision research, little attention has been paid to perceiving and…
The puzzle of computer vision might find new challenging solutions when we realize that most successful methods are working at image level, which is remarkably more difficult than processing directly visual streams. In this paper, we claim…
Video motion magnification could directly highlight subsurface blood vessels in endoscopic video in order to prevent inadvertent damage and bleeding. Applying motion filters to the full surgical image is however sensitive to residual motion…
Motion blur is a fundamental problem in computer vision as it impacts image quality and hinders inference. Traditional deblurring algorithms leverage the physics of the image formation model and use hand-crafted priors: they usually produce…
The puzzle of computer vision might find new challenging solutions when we realize that most successful methods are working at image level, which is remarkably more difficult than processing directly visual streams, just as happens in…
Motion Magnification (MM) is a collection of relative recent techniques within the realm of Image Processing. The main motivation of introducing these techniques in to support the human visual system to capture relevant displacements of an…
Learning with neural networks from a continuous stream of visual information presents several challenges due to the non-i.i.d. nature of the data. However, it also offers novel opportunities to develop representations that are consistent…