Seamless video editing

This paper presents a new framework for seamless video editing in the gradient domain. The spatio-temporal gradient fields of target videos are modified or mixed to generate a new gradient field, which is usually not integrable. We propose a 3D video integration algorithm, which finds a potential function, whose gradient field is closest to the resulting gradient field in the sense of least squares. The video is reconstructed by solving a 3D Poisson equation. We use a fast and accurate 3D discrete Poisson solver using diagonal multigrids. A set of gradient operators is defined for user interaction. The resulting video has temporal coherency and no artifacts. We evaluate our algorithm using a variety of examples.

[1]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[2]  Ramesh Raskar,et al.  Image Fusion for Context Enhancement , 2003 .

[3]  Lawrence B. Wolff,et al.  A new visualization paradigm for multispectral imagery and data fusion , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[4]  Michael Elad,et al.  A Variational Framework for Retinex , 2002, IS&T/SPIE Electronic Imaging.

[5]  Patrick Pérez,et al.  Poisson image editing , 2003, ACM Trans. Graph..

[6]  Leonard McMillan,et al.  Proscenium: a framework for spatio-temporal video editing , 2003, ACM Multimedia.

[7]  Edward H. Adelson,et al.  A multiresolution spline with application to image mosaics , 1983, TOGS.

[8]  Adam Finkelstein,et al.  Stylized video cubes , 2002, SCA '02.

[9]  Guillermo Sapiro,et al.  Image inpainting , 2000, SIGGRAPH.

[10]  A. J. Roberts.  Fast and accurate multigrid solution of Poissons equation using diagonally oriented grids , 1999 .

[11]  Mark S. Drew,et al.  Removing Shadows from Images , 2002, ECCV.

[12]  Dani Lischinski,et al.  Gradient Domain High Dynamic Range Compression , 2023 .

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