1 / 13

Learning the “Epitome” of a Video Sequence Information Processing Workshop 2004

Learning the “Epitome” of a Video Sequence Information Processing Workshop 2004. Vincent Cheung Probabilistic and Statistical Inference Group Electrical & Computer Engineering University of Toronto Toronto, Ontario, Canada Advisor: Dr. Brendan J. Frey. Outline. Image epitome What? Why?

Download Presentation

Learning the “Epitome” of a Video Sequence Information Processing Workshop 2004

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Learning the “Epitome”of a Video SequenceInformation Processing Workshop 2004 Vincent Cheung Probabilistic and Statistical Inference Group Electrical & Computer Engineering University of Toronto Toronto, Ontario, Canada Advisor: Dr. Brendan J. Frey Aug. 11, 2004

  2. Outline • Image epitome • What? • Why? • Implementation computation issues • Efficiently implementing the learning algorithm • Video epitome • Extension to videos • Video inpainting Cheung

  3. Image Epitome • Jojic, N., Frey, B., & Kannan, A. (2003). Epitomic analysis of appearance and shape. In Proc. IEEE ICCV. • Miniature, condensed version of the image • Accurately accounts for the interesting properties of the image • Applications • object detection • texture segmentation • image retrieval • compression Cheung

  4. Image Epitome Examples Cheung

  5. Training Set Input image Epitome Sample Patches Unsupervised Learning e – epitome Tk – mapping Zk – image patch Bayesiannetwork e T1 T2 TM … Z1 Z2 ZM Learning the Image Epitome Cheung

  6. + - + - Shifted Cumulative Sum Algorithm Cheung

  7. Collecting Sufficient Statistics Cheung

  8. Extending Epitomes to Videos • Desire a miniature, condensed version of a video sequence • Want it to accurately account for the interesting properties of the video • Applications • optic flow • segmentation • texture transfer • layer separation • compression • noise reduction • inpainting Cheung

  9. Training Set Input Video Video Epitome Unsupervised Learning Sample Patches Frame 3 Frame 2 Frame 1 Video Epitome Cheung

  10. Temporally Compressed Spatially Compressed Video Epitome Example Cheung

  11. Video Inpainting (1) • Fill in missing portions of a video • damaged films • occluding objects • Reconstruct the missing pixels from the video epitome Cheung

  12. Video Inpainting (2) Cheung

  13. Conclusion • Improved the efficiency of learning image epitomes • Extended the concept of epitomes to video sequences • Demonstrated the ability of video epitomes to model motion patterns through video inpainting Cheung

More Related