Automated video looping with progressive dynamism

Liao, Zuwei; Joshi, Neel; Hoppe, Hugues

doi:10.1145/2461912.2461950

Cited by 43 publications

(60 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The consistency constraints are adaptively attenuated by recognizing that discontinuities are less perceptible in high-frequency regions [Kwatra et al 2003]. Troublesome scene regions are replaced by static (nonlooping) pixels, either using assisted segmentation [Agarwala et al 2005;Tompkin et al 2011;Bai et al 2012;Joshi et al 2012] or as part of the optimization [Liao et al 2013]. However, for some scenes there may be little dynamism left.…”

Section: Input Videomentioning

confidence: 99%

“…We review prior work, including the framework of [Liao et al 2013] upon which we build, then present our processing pipeline and contributions in Section 3. …”

Section: Fast Loop Computationmentioning

confidence: 99%

“…Our work builds on the automated technique of Liao et al [2013] which optimizes a looping period px and start frame sx at each pixel:…”

Section: 270mentioning

confidence: 99%

“…Several techniques create looping videos from short input videos [e.g., Schödl et al 2000;Kwatra et al 2003;Agarwala et al 2005;Couture et al 2011;Liao et al 2013]. The general approach is to assemble content from the original video such that 3D spatiotemporal neighborhoods of the resulting video loop are consistent with those of the input video.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fast computation of seamless video loops

Liao¹,

Finch

Hoppe

2015

ACM Trans. Graph.

Self Cite

View full text Add to dashboard Cite

Short looping videos concisely capture the dynamism of natural scenes. Creating seamless loops usually involves maximizing spatiotemporal consistency and applying Poisson blending. We take an end-to-end view of the problem and present new techniques that jointly improve loop quality while also significantly reducing processing time. A key idea is to relax the consistency constraints to anticipate the subsequent blending, thereby enabling looping of lowfrequency content like moving clouds and changing illumination. We also analyze the input video to remove an undesired bias toward short loops. The quality gains are demonstrated visually and confirmed quantitatively using a new gradient-domain consistency metric. We improve system performance by classifying potentially loopable pixels, masking the 2D graph cut, pruning graph-cut labels based on dominant periods, and optimizing on a coarse grid while retaining finer detail. Together these techniques reduce computation times from tens of minutes to nearly real-time.

show abstract

Section: Input Videomentioning

confidence: 99%

“…We review prior work, including the framework of [Liao et al 2013] upon which we build, then present our processing pipeline and contributions in Section 3. …”

Section: Fast Loop Computationmentioning

confidence: 99%

“…Our work builds on the automated technique of Liao et al [2013] which optimizes a looping period px and start frame sx at each pixel:…”

Section: 270mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fast computation of seamless video loops

Liao¹,

Finch

Hoppe

2015

ACM Trans. Graph.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Users simply capture a short hand-held video of a person, push a button, and our system outputs a portrait cinemagraph. There are a number of recent techniques for creating cinemagraphs, including mobile apps [3, 4, 5] and several research systems [107,59,116,71]. However, these techniques are all challenged by portraits, because people are not good at keeping their head and body perfectly still.…”

Section: Introductionmentioning

confidence: 99%

Selectively De-animating and Stabilizing Videos

Bai¹

2014

View full text Add to dashboard Cite

This thesis presents three systems for editing the motion of videos. First, selectively deanimating videos seeks to remove the large-scale motions of one or more objects so that other motions are easier to see. The user draws strokes to indicate the regions that should be immobilized, and our algorithm warps the video to remove large-scale motion in regions while leaving finer-scale, relative motions intact. We then use a graph-cut-based optimization to composite the warped video with still frames from the input video to remove unwanted background motion. Our technique enables applications such as clearer motion visualization, simpler creation of artistic cinemagraphs, and new ways to edit appearance and motion paths in video. Second, we design a fully automatic system to create portrait cinemagraphs by tracking facial features and de-animating the video with respect to the face and torso. We then generate compositing weights automatically to create the final cinemagraph portraits.Third, we present a user-assisted video stabilization algorithm that is able to stabilize challenging videos when state-of-the-art automatic algorithms fail to generate a satisfactory result. Our system introduces two new modes of interaction that allow the user to improve an unsatisfactory automatically stabilized video. First, we cluster tracks and visualize them on the warped video. The user ensures that appropriate tracks are selected by clicking on track clusters to include or exclude them to guide the stabilization. Second, the user can directly specify how regions in the output video should look by drawing quadrilaterals to select and deform parts of the frame. Our algorithm then computes a stabilized video using the user-selected tracks, while respecting the user-modified regions.

show abstract

Learning-Based Video Motion Magnification

Oh¹,

Jaroensri²,

Kim³

et al. 2018

Computer Vision – ECCV 2018

105

104

View full text Add to dashboard Cite

Video motion magnification techniques allow us to see small motions previously invisible to the naked eyes, such as those of vibrating airplane wings, or swaying buildings under the influence of the wind. Because the motion is small, the magnification results are prone to noise or excessive blurring. The state of the art relies on hand-designed filters to extract representations that may not be optimal. In this paper, we seek to learn the filters directly from examples using deep convolutional neural networks. To make training tractable, we carefully design a synthetic dataset that captures small motion well, and use two-frame input for training. We show that the learned filters achieve high-quality results on real videos, with less ringing artifacts and better noise characteristics than previous methods. While our model is not trained with temporal filters, we found that the temporal filters can be used with our extracted representations up to a moderate magnification, enabling a frequencybased motion selection. Finally, we analyze the learned filters and show that they behave similarly to the derivative filters used in previous works. Our code, trained model, and datasets will be available online.

show abstract

Automated video looping with progressive dynamism

Cited by 43 publications

References 29 publications

Fast computation of seamless video loops

Fast computation of seamless video loops

Selectively De-animating and Stabilizing Videos

Learning-Based Video Motion Magnification

Contact Info

Product

Resources

About