Video textures

By Arno Schödl, Richard Szeliski, David Salesin, Irfan Essa. International Conference on Computer Graphics and Interactive Techniques, 2000

660 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b1cfc0aab0b3b4c2abf030479d8a663d747a6501

How researchers see this paper

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

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Motion synthesis from annotations (2003, background): “The sampling can also be done in the motion domain to pick clips of motions to establish certain simple constraints [Lamouret and van de Panne 1996; Schodl et al. 2000].”
Interactive motion generation from examples (2002, background): “The sampling can also be done in the motion domain to pick clips of motions to establish certain simple constraints [Lamouret and van de Panne 1996; Schodl et al. 2000].”
Image Completion Using Efficient Belief Propagation Via Priority Scheduling and Dynamic Pruning (2007, background): “[21] are able to synthesize new video textures simply by rearranging the”
WYSIWYG NPR: drawing strokes directly on 3D models (2002, neutral): “Other researchers, for example, Schoeneman et al. [1993] and Poulin et al.”
Video-to-Video Synthesis (2018, methodology): “Our method is inspired by previous application-speciﬁc video synthesis methods [58,60,61,75].”
Video Inpainting of Complex Scenes (2014, background): “Second, while the problem of recreating video textures is a research subject in its own right and algorithms have been developed for their synthesis [16, 27, 38], ours is the first algorithm to achieve this within an inpainting framework.”
Recognizing action at a distance (2003, background): “The idea is in the spirit of Video Textures [14], except that we would like to have control over the actions that are being synthesized.”
Spacetime faces: high resolution capture for modeling and animation (2004, methodology): “Our approach adapts related graph techniques used in video textures [Sch¤odl et al. 2000] and character animation [Kovar et al. 2002; Arikan and Forsyth 2002; Lee et al. 2002] to the domain of face animation.”
Motion magnification (2005, background): “Video textures [Schodl et al. 2000] analyzes the overall similarity of all frames to identify candidate temporal jumps in a modified playback of the video.”
Dynamic Textures (2003, background): “[34] address the problem by finding transition points in the original video sequence where the video can be looped back on itself in a minimally obtrusive way.”
Implicit Probabilistic Models of Human Motion for Synthesis and Tracking (2002, background): “More closely related to the work described here is the work on video textures [35] which uses a pixel-based match metric to construct a matrix of probabilities that captures the similarities between frames in a video sequence and that can be used to transition between frames to construct an infinite”
Data-driven visual similarity for cross-domain image matching (2011, background): “…super-resolution and de-noising [Freeman et al. 2002; Buades et al. 2005; HaCohen et al. 2010], texture and video synthesis [Efros and Freeman 2001; Schodl et al. 2000], image analogies [Hertzmann et al. 2001], automatic colorization [Torralba et al. 2008], scene and video completion [Wexler et…”
Synthesising Dynamic Textures using Convolutional Neural Networks (2017, background): “[1, 2, 3, 4, 5, 6, 7]) and recently spatio-temporal Convolutional Neural Networks (CNNs) were proposed to generate samples of dynamic textures [8].”
Event-based analysis of video (2001, methodology): “[23] used the term “video textures” with a different meaning - for synthesizing video by temporally shuffling frames.”
Video-based face recognition using probabilistic appearance manifolds (2003, background): “We conclude with remarks and future work in Section 5.”