Representing moving images with layers

@article{Wang1994RepresentingMI,
  title={Representing moving images with layers},
  author={John Y. A. Wang and Edward H. Adelson},
  journal={IEEE transactions on image processing : a publication of the IEEE Signal Processing Society},
  year={1994},
  volume={3 5},
  pages={
          625-38
        }
}
We describe a system for representing moving images with sets of overlapping layers. Each layer contains an intensity map that defines the additive values of each pixel, along with an alpha map that serves as a mask indicating the transparency. The layers are ordered in depth and they occlude each other in accord with the rules of compositing. Velocity maps define how the layers are to be warped over time. The layered representation is more flexible than standard image transforms and can… CONTINUE READING

Figures and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 848 CITATIONS

Rekurrente visuelle Bewegungssegmentierung

  • Automatisierungstechnik
  • 2006
VIEW 9 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

PR OO LAMP : 3 D layered , adaptive-resolution , and multi-perspective panorama — a new scene representation

Zhigang Zhua, Allen R. Hansonb
  • 2004
VIEW 7 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

Bayesian motion estimation and segmentation

VIEW 20 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Region-Based Parametric Motion Segmentation Using Color Information

  • Graphical Models and Image Processing
  • 1998
VIEW 8 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Computer Vision – ECCV 2014

  • Lecture Notes in Computer Science
  • 2014
VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Perception-oriented video coding based on texture analysis and synthesis

  • 2009 16th IEEE International Conference on Image Processing (ICIP)
  • 2009
VIEW 13 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Bayesian Video Matting Using Motion Based Segmentation

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Segmentation of Tracking Sequences Using Dynamically Updated Adaptive Learning

  • IEEE Transactions on Image Processing
  • 2008
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

1994
2019

CITATION STATISTICS

  • 75 Highly Influenced Citations

  • Averaged 12 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 17 REFERENCES

Unified computational theory for motion transparency and motion boundaries based on eigenenergy analysis

  • Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1991
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Layered representation for image sequence coding

  • 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 1993
VIEW 1 EXCERPT

Layered representation for motion analysis

  • Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
  • 1993
VIEW 1 EXCERPT

Hierarchial model-based motion estima- tion

J. Bergen, P. Anandan, K. Hana, R. Hin- gorini al
  • In Proc. Second European Conf. on Comput. Vision,
  • 1992
VIEW 1 EXCERPT

Image sequence enhancement using multiple motions analysis

  • Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1992
VIEW 2 EXCERPTS

Motion estimation with detection of occlusion areas

  • [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 1992
VIEW 1 EXCERPT

Robust dynamic motion estimation over time

  • Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1991
VIEW 1 EXCERPT

Robust estimation of a multi-layered motion representation

  • Proceedings of the IEEE Workshop on Visual Motion
  • 1991
VIEW 2 EXCERPTS

Computing two motions from three frames

  • [1990] Proceedings Third International Conference on Computer Vision
  • 1990
VIEW 1 EXCERPT