Dynamic Textures

Dynamic Textures

Details

A dynamic texture (DT) is the temporal extension of 2D texture. Even though the overall global motion of a DT may be perceived by humans as simple and coherent, the underlying local motion is complex and stochastic. DT models are developed and applied to DT synthesis, recognition, and compression. Some experimental results are provided here. Below are some sample publications.

Selected Publications



 
 

 Maximum Margin Distance Learning for Dynamic Texture Recognition




 
 

 

Phase Based Modeling of Dynamic Textures​




 
 

Publications

  1. Bernard Ghanem and Narendra Ahuja, "Maximum Margin Distance Learning for Dynamic Texture Recognition", European Conference on Computer Vision (ECCV 2010)
  2. Bernard Ghanem and Narendra Ahuja, "Sparse Coding of Linear Dynamical Systems with an Application to Dynamic Texture Recognition", International Conference on Pattern Recognition (ICPR 2010)
  3. Bernard Ghanem and Narendra Ahuja, "Extracting a Fluid Dynamic Texture and the Background from Video", Conference on Computer Vision and Pattern Recognition (CVPR 2008)
  4. Bernard Ghanem and Narendra Ahuja, "Phase Based Modeling of Dynamic Textures", International Conference on Computer Vision (ICCV 2007)
  5. Bernard Ghanem and Narendra Ahuja, "Phase PCA for Dynamic Texture Video Compression", International Conference on Image Processing (ICIP 2007)