Abstract | ||
---|---|---|
Dynamic textures are sequences of images of moving scenes that exhibit certain stationarity properties in time; these include sea-waves, smoke, foliage, whirlwind etc. We present a characterization of dynamic textures that poses the problems of modeling, learning, recognizing and synthesizing dynamic textures on a firm analytical footing. We borrow tools from system identification to capture the “essence” of dynamic textures; we do so by learning (i.e. identifying) models that are optimal in the sense of maximum likelihood or minimum prediction error variance. For the special case of second-order stationary processes, we identify the model sub-optimally in closed-form. Once learned, a model has predictive power and can be used for extrapolating synthetic sequences to infinite length with negligible computational cost. We present experimental evidence that, within our framework, even low-dimensional models can capture very complex visual phenomena. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1023/A:1021669406132 | International Journal of Computer Vision |
Keywords | DocType | Volume |
textures,dynamic scene analysis,3D textures,minimum description length,image compression,generative model,prediction error methods,ARMA model,subspace system identification,canonical correlation,learning | Journal | 51 |
Issue | Citations | PageRank |
2 | 241 | 23.46 |
References | Authors | |
29 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gianfranco Doretto | 1 | 1026 | 78.58 |
Alessandro Chiuso | 2 | 1159 | 103.17 |
Ying Nian Wu | 3 | 1652 | 267.72 |
Stefano Soatto | 4 | 4967 | 350.34 |