Slippage-free background replacement for hand-held video

We introduce a method for replacing the background in a video of a moving foreground subject, when both the source video capturing the subject, and the target video capturing the new background scene, are natural videos, casually captured using a freely moving hand-held camera. We assume that the foreground subject has already been extracted, and focus on the challenging task of generating a video with a new background, such that the new background motion appears compatible with the original one. Failure to match the motion results in disturbing slippage or moonwalk artifacts, where the subject's feet appear to slide or slip over the ground. While matching the motion across the entire frame is impossible for scenes with differing geometry, we aim to match the local motion of the ground in the vicinity of the subject. This is achieved by reordering and warping the available target background frames in a manner that optimizes a suitably designed objective function.

[1]  Raanan Fattal,et al.  Video stabilization using epipolar geometry , 2012, TOGS.

[2]  Michael Gleicher,et al.  Subspace video stabilization , 2011, TOGS.

[3]  Hans-Peter Seidel,et al.  Video-based characters: creating new human performances from a multi-view video database , 2011, ACM Trans. Graph..

[4]  Kwan-Liu Ma,et al.  Graph-based fire synthesis , 2011, SCA '11.

[5]  David Salesin,et al.  Video matting of complex scenes , 2002, SIGGRAPH.

[6]  David Salesin,et al.  Panoramic video textures , 2005, SIGGRAPH 2005.

[7]  Marcus A. Magnor,et al.  View and Time Interpolation in Image Space , 2008, Comput. Graph. Forum.

[8]  Micah K. Johnson,et al.  Multi-scale image harmonization , 2010, ACM Trans. Graph..

[9]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .

[10]  Richard Szeliski,et al.  Video textures , 2000, SIGGRAPH.

[11]  Atsushi Nakazawa,et al.  Human video textures , 2009, I3D '09.

[12]  Jian Sun,et al.  Bundled camera paths for video stabilization , 2013, ACM Trans. Graph..

[13]  Irfan A. Essa,et al.  Auto-directed video stabilization with robust L1 optimal camera paths , 2011, CVPR 2011.

[14]  David Salesin,et al.  Keyframe-based tracking for rotoscoping and animation , 2004, SIGGRAPH 2004.

[15]  David Salesin,et al.  Panoramic video textures , 2005, ACM Trans. Graph..

[16]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[17]  Maneesh Agrawala,et al.  Interactive video cutout , 2005, SIGGRAPH 2005.

[18]  Ken-ichi Anjyo,et al.  Creating Fluid Animation from a Single Image using Video Database , 2011, Comput. Graph. Forum.

[19]  Wojciech Matusik,et al.  Multi-scale image harmonization , 2010, SIGGRAPH 2010.

[20]  Zeev Farbman,et al.  Tonal stabilization of video , 2011, SIGGRAPH 2011.

[21]  Michael Gleicher,et al.  Re-cinematography: Improving the camerawork of casual video , 2008, TOMCCAP.

[22]  Maneesh Agrawala,et al.  Interactive video cutout , 2005, ACM Trans. Graph..

[23]  Seth J. Teller,et al.  Video matching , 2004, Encyclopedia of Multimedia.

[24]  Richard Szeliski,et al.  Efficiently registering video into panoramic mosaics , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[25]  James F. Blinn,et al.  Blue screen matting , 1996, SIGGRAPH.

[26]  Markus H. Gross,et al.  Novel‐View Synthesis of Outdoor Sport Events Using an Adaptive View‐Dependent Geometry , 2012, Comput. Graph. Forum.

[27]  Jan Kautz,et al.  Video-based characters: creating new human performances from a multi-view video database , 2011, SIGGRAPH 2011.

[28]  Michael Gleicher,et al.  Content-preserving warps for 3D video stabilization , 2009, ACM Trans. Graph..

[29]  David Salesin,et al.  Keyframe-based tracking for rotoscoping and animation , 2004, ACM Trans. Graph..

[30]  Guillermo Sapiro,et al.  Video SnapCut: robust video object cutout using localized classifiers , 2009, SIGGRAPH 2009.