Transfusive Image Manipulation

publication
ACM SIGGRAPH ASIA 2012
authors
Kaan Yücer, Alec Jacobson, Alexander Sorkine-Hornung, Olga Sorkine-Hornung

Vines, cracks and even new windows are added to an image of a church and then propagated to 8 other images.

A trained artist makes detailed edits to a single source image (left) and our method transfers the edits to the 8 target images (right).

abstract

We present a method for consistent automatic transfer of edits applied to one image to many other images of the same object or scene. By introducing novel, content-adaptive weight functions we enhance the non-rigid alignment framework of Lucas-Kanade to robustly handle changes of view point, illumination and non-rigid deformations of the subjects. Our weight functions are content-aware and possess high-order smoothness, enabling to define high-quality image warping with a low number of parameters using spatially-varying weighted combinations of affine deformations. Optimizing the warp parameters leads to subpixel-accurate alignment while maintaining computation efficiency. Our method allows users to perform precise, localized edits such as simultaneous painting on multiple images in real-time, relieving them from tedious and repetitive manual reapplication to each individual image.

downloads

accompanying video

earlier technical report

A Cotangent Laplacian for Images as Surfaces by Alec Jacobson and Olga Sorkine, 2012 (BibTeX)
Abstract: By embedding images as surfaces in a high dimensional coordinate space defined by each pixel’s Cartesian coordinates and color values, we directly define and employ cotangent-based, discrete differential-geometry operators. These operators define discrete energies useful for image segmentation and colorization.

acknowledgements

We are grateful to Yael Pritch and Ilya Baran for internal reviews; Alessia Marra for providing professional edits; Maurizio Nitti, Leila Gangji, Dylan Zehr, Katie Anderson, and Alex Schiebel for modeling; Mykl Roventine, Jonathunder, ZeroOne, <<<TheOne>>>, Erik Hagreis, roblisameehan, *christopher*, and Jason Jenkins for their Creative Commons images; and Sam Hasinoff, Yoav HaCohen and Henning Zimmer for helping with comparisons.