skip to main content
article

Smooth Loops from Unconstrained Video

Published:01 July 2015Publication History
Skip Abstract Section

Abstract

Converting unconstrained video sequences into videos that loop seamlessly is an extremely challenging problem. In this work, we take the first steps towards automating this process by focusing on an important subclass of videos containing a single dominant foreground object. Our technique makes two novel contributions over previous work: first, we propose a correspondence-based similarity metric to automatically identify a good transition point in the video where the appearance and dynamics of the foreground are most consistent. Second, we develop a technique that aligns both the foreground and background about this transition point using a combination of global camera path planning and patch-based video morphing. We demonstrate that this allows us to create natural, compelling, loopy videos from a wide range of videos collected from the internet.

References

  1. <label>{APS*14}</label> Arev I., Park H.S., Sheikh Y., Hodgins J., Shamir A.: Automatic editing of footage from multiple social cameras. ACM Trans. on Graph. Proc. SIGGRAPH Volume 33, Issue 4 July 2014, pp.81:1-81:11. 9 Google ScholarGoogle ScholarDigital LibraryDigital Library
  2. <label>{AZP*05}</label> Agarwala A., Zheng K.C., Pal C., Agrawala M., Cohen M., Curless B., Salesin D., Szeliski R.: Panoramic video textures. ACM Trans. on Graph. Proc. SIG-GRAPH Volume 24, Issue 3 July 2005, pp.821-827. 2 Google ScholarGoogle ScholarDigital LibraryDigital Library
  3. <label>{BAAR12}</label> Bai J., Agarwala A., Agrawala M., Ramamoorthi R.: Selectively de-animating video. ACM Trans. on Graph. Proc. SIGGRAPH Volume 31, Issue 4 July 2012, pp.66:1-66:10. 2 Google ScholarGoogle ScholarDigital LibraryDigital Library
  4. <label>{BBPP10}</label> Ballan L., Brostow G.J., Puwein J., Pollefeys M.: Unstructured video-based rendering: Interactive exploration of casually captured videos. ACM Trans. on Graph. Proc. SIGGRAPH Volume 29, Issue 4 July 2010, pp.87:1-87:11. 9 Google ScholarGoogle ScholarDigital LibraryDigital Library
  5. <label>{BLA12}</label> Berthouzoz F., Li W., Agrawala M.: Tools for placing cuts and transitions in interview video. ACM Trans. Graph. Volume 31, Issue 4 July 2012, pp.67:1-67:8. 2, 9 Google ScholarGoogle ScholarDigital LibraryDigital Library
  6. <label>{Car}</label> CARRÉ L. :. URL: "http://lillicarre.tumblr.com/". 1Google ScholarGoogle Scholar
  7. <label>{DCWS03}</label> Doretto G., Chiuso A., Wu Y., Soatto S.: Dynamic textures. IJCV Volume 51, Issue 2 2003, pp.91-109. 2 Google ScholarGoogle ScholarDigital LibraryDigital Library
  8. <label>{FS11}</label> Freeman J., Simoncelli E.P.: Metamers of the ventral stream. Nature neuroscience Volume 14, Issue 9 2011, pp.1195-1201. 1Google ScholarGoogle Scholar
  9. <label>{Gol07}</label> Goldman D.R.: A framework for video annotation, visualization, and interaction. PhD thesis, University of Washington, 2007. 2Google ScholarGoogle Scholar
  10. <label>{Gom99}</label> Gomes J.: Warping and Morphing of Graphical Objects. Morgan Kaufmann, 1999. 2Google ScholarGoogle Scholar
  11. <label>{HSGL11}</label> HaCohen Y., Shechtman E., Goldman D.B., Lischinski D.: Non-rigid dense correspondence with applications for image enhancement. ACM Trans. on Graph. Proc. SIGGRAPH Volume 30, Issue 4 2011, pp.70:1-70:9. 2, 4, 8 Google ScholarGoogle ScholarDigital LibraryDigital Library
  12. <label>{Inc}</label> Inci E. :. URL: "http://erdalinci.tumblr.com/". 1Google ScholarGoogle Scholar
  13. <label>{JMD*12}</label> Joshi N., Mehta S., Drucker S., Stollnitz E., Hoppe H., Uyttendaele M., Cohen M.: Cliplets: Juxtaposing still and dynamic imagery</otherTitle>. In <otherTitle>Proc. UIST 2012, pp. pp.251-260. 2 Google ScholarGoogle ScholarDigital LibraryDigital Library
  14. <label>{KSE*03}</label> Kwatra V., Schödl A., Essa I., Turk G., Bobick A.: Graphcut textures: Image and video synthesis using graph cuts. ACM Trans. on Graph. Proc. SIGGRAPH Volume 22, Issue 3 July 2003, pp.277-286. 2 Google ScholarGoogle ScholarDigital LibraryDigital Library
  15. <label>{KSSGS11}</label> Kemelmacher-Shlizerman I., Shechtman E., Garg R., Seitz S.M.: Exploring photobios. ACM Trans. on Graph. Proc. SIGGRAPH Volume 30, Issue 4 July 2011, pp.61:1-61:10. 2 Google ScholarGoogle ScholarDigital LibraryDigital Library
  16. <label>{LJH13}</label> Liao Z., Joshi N., Hoppe H.: Automated video looping with progressive dynamism. ACM Trans. on Graph. Proc. SIGGRAPH Volume 32, Issue 4 July 2013, pp.77:1-77:10. 2, 3 Google ScholarGoogle ScholarDigital LibraryDigital Library
  17. <label>{LLN*14}</label> Liao J., Lima R.S., Nehab D., Hoppe H., Sander P.V.: Semi-automated video morphing. Comp. Graph. Forum Proc. EGSR Volume 33, Issue 4 2014, pp.51-60. 2 Google ScholarGoogle ScholarDigital LibraryDigital Library
  18. <label>{LTK12}</label> Levieux P., Tompkin J., Kautz J.: Interactive viewpoint video textures</otherTitle>. In <otherTitle>Proc. CVMP December 2012. 3 Google ScholarGoogle ScholarDigital LibraryDigital Library
  19. <label>{PF13}</label> Papazoglou A., Ferrari V.: Fast object segmentation in unconstrained video</otherTitle>. <otherTitle>ICCV 2013. 3, 8Google ScholarGoogle Scholar
  20. <label>{Raj}</label> Rajkovic M. :. URL: "http://milosrajk.ovic.tumblr.com/". 1Google ScholarGoogle Scholar
  21. <label>{RKB04}</label> Rother C., Kolmogorov V., Blake A.: GrabCut: Interactive foreground extraction using iterated graph cuts</otherTitle>. In <otherTitle>ACM Trans. on Graph. Proc. SIGGRAPH 2004, pp. pp.309-314. 3 Google ScholarGoogle ScholarDigital LibraryDigital Library
  22. <label>{RWSG13}</label> Rãijegg J., Wang O., Smolic A., Gross M.: Ducttake: Spatiotemporal video compositing. Comp. Graph. Forum Volume 32, Issue 2pt1 2013, pp.51-61. 2Google ScholarGoogle Scholar
  23. <label>{SRAIS10}</label> Shechtman E., Rav-Acha A., Irani M., Seitz S.M.: Regenerative morphing</otherTitle>. In <otherTitle>CVPR 2010, pp. pp.615-622. 2, 6Google ScholarGoogle Scholar
  24. <label>{SRDB10}</label> Sun D., Roth S., Darmstadt T., Black M.: Secrets of optical Flow Estimation and Their Principles</otherTitle>. <otherTitle>CVPR 2010.Google ScholarGoogle Scholar
  25. <label>{SSSE00}</label> Schödl A., Szeliski R., Salesin D.H., Essa I.: Video Textures</otherTitle>. In <otherTitle>ACM Trans. on Graph. Proc. SIGGRAPH 2000, pp. pp.489-498. 1, 2, 3, 4, 5 Google ScholarGoogle ScholarDigital LibraryDigital Library
  26. <label>{TPSK11}</label> Tompkin J., Pece F., Subr K., Kautz J.: Towards moment images: Automatic cinemagraphs</otherTitle>. In <otherTitle>Proc. CVMP November 2011, pp. pp.87-93. 2 Google ScholarGoogle ScholarDigital LibraryDigital Library
  27. <label>{Vin14}</label> Vine statistics, Aug 2014. URL: "http://blog.vine.co/post/95288683756/new-vine-camera-shoot-import-edit-and-share". 1Google ScholarGoogle Scholar
  28. <label>{ZCA*09}</label> Zheng K.C., Colburn A., Agarwala A., Agrawala M., Curless B., Salesin D., Cohen M.: Parallax photography: Creating 3D cinematic effects from stills. In Graph. Interface 2009 May 2009. 2Google ScholarGoogle Scholar

Recommendations

Comments

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Sign in

Full Access

  • Published in

    cover image Computer Graphics Forum
    Computer Graphics Forum  Volume 34, Issue 4
    July 2015
    167 pages
    ISSN:0167-7055
    EISSN:1467-8659
    Issue’s Table of Contents

    Publisher

    The Eurographs Association & John Wiley & Sons, Ltd.

    Chichester, United Kingdom

    Publication History

    • Published: 1 July 2015

    Qualifiers

    • article