Video Painting Based on a Stabilized Time-Varying Flow Field

Jong-Chul Yoon; In-Kwon Lee; Henry Kang

doi:10.1109/TVCG.2011.47

Video Painting Based on a Stabilized Time-Varying Flow Field

Jong-Chul Yoon, In-Kwon Lee, Henry Kang

University of Missouri-St. Louis

Research output: Contribution to journal › Article › peer-review

Abstract

We present a method for constructing 3D feature flow from video and its application to video stylization. Our method extracts smoothly aligned 3D vectors that describe the smallest variation of colors within a spatiotemporal video cube, and thus effectively preserves both spatial and temporal coherence in a relatively inexpensive manner. As an application of this flow field we present a particle-based video stylization technique to rerender the video in a feature enhancing, painterly style. Our method consists of per-pixel operations and is suitable for GPU implementation, which enables real-time video stylization.

Original language	American English
Pages (from-to)	58
Number of pages	67
Journal	IEEE Transactions on Visualization and Computer Graphics
Volume	18
Issue number	1
DOIs	https://doi.org/10.1109/TVCG.2011.47
State	Published - Jan 1 2012

Keywords

Three dimensional displays
Pixel
Painting
Image color analysis
Rendering (computer graphics)
Color
Coherence
Nonphotorealistic rendering
flow-based filtering
video abstraction
painterly rendering

Disciplines

Painting
Arts and Humanities
Artificial Intelligence and Robotics

Access to Document

10.1109/TVCG.2011.47

Cite this

@article{069c027bb1404b228f4db01cb018bcde,

title = "Video Painting Based on a Stabilized Time-Varying Flow Field",

abstract = "We present a method for constructing 3D feature flow from video and its application to video stylization. Our method extracts smoothly aligned 3D vectors that describe the smallest variation of colors within a spatiotemporal video cube, and thus effectively preserves both spatial and temporal coherence in a relatively inexpensive manner. As an application of this flow field we present a particle-based video stylization technique to rerender the video in a feature enhancing, painterly style. Our method consists of per-pixel operations and is suitable for GPU implementation, which enables real-time video stylization.",

keywords = "Three dimensional displays, Pixel, Painting, Image color analysis, Rendering (computer graphics), Color, Coherence, Nonphotorealistic rendering, flow-based filtering, video abstraction, painterly rendering",

author = "Jong-Chul Yoon and In-Kwon Lee and Henry Kang",

note = "Fig. 5. The effect of particle velocity vg on the degree of abstraction: (a) input image; (b) vg ¼ 0:5; and (c) vg ¼ 2. - {"}Video Painting Based on a Stabilized Time-Varying Flow Field{"}",

year = "2012",

month = jan,

day = "1",

doi = "10.1109/TVCG.2011.47",

language = "American English",

volume = "18",

pages = "58",

journal = "IEEE Transactions on Visualization and Computer Graphics",

number = "1",

}

TY - JOUR

T1 - Video Painting Based on a Stabilized Time-Varying Flow Field

AU - Yoon, Jong-Chul

AU - Lee, In-Kwon

AU - Kang, Henry

N1 - Fig. 5. The effect of particle velocity vg on the degree of abstraction: (a) input image; (b) vg ¼ 0:5; and (c) vg ¼ 2. - "Video Painting Based on a Stabilized Time-Varying Flow Field"

PY - 2012/1/1

Y1 - 2012/1/1

N2 - We present a method for constructing 3D feature flow from video and its application to video stylization. Our method extracts smoothly aligned 3D vectors that describe the smallest variation of colors within a spatiotemporal video cube, and thus effectively preserves both spatial and temporal coherence in a relatively inexpensive manner. As an application of this flow field we present a particle-based video stylization technique to rerender the video in a feature enhancing, painterly style. Our method consists of per-pixel operations and is suitable for GPU implementation, which enables real-time video stylization.

AB - We present a method for constructing 3D feature flow from video and its application to video stylization. Our method extracts smoothly aligned 3D vectors that describe the smallest variation of colors within a spatiotemporal video cube, and thus effectively preserves both spatial and temporal coherence in a relatively inexpensive manner. As an application of this flow field we present a particle-based video stylization technique to rerender the video in a feature enhancing, painterly style. Our method consists of per-pixel operations and is suitable for GPU implementation, which enables real-time video stylization.

KW - Three dimensional displays

KW - Pixel

KW - Painting

KW - Image color analysis

KW - Rendering (computer graphics)

KW - Color

KW - Coherence

KW - Nonphotorealistic rendering

KW - flow-based filtering

KW - video abstraction

KW - painterly rendering

UR - https://www.semanticscholar.org/paper/Video-Painting-Based-on-a-Stabilized-Time-Varying-Yoon-Lee/89e9a97e3a30f807730b5ccea8303ee566ca1e31/figure/5

U2 - 10.1109/TVCG.2011.47

DO - 10.1109/TVCG.2011.47

M3 - Article

VL - 18

SP - 58

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

IS - 1

ER -

Video Painting Based on a Stabilized Time-Varying Flow Field

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Cite this