Transfusive Image Manipulation
Kaan Yücer (Disney Research Zurich)
Alec Jacobson (ETH Zurich)
Alexander Sorkine-Hornung (Disney Research Zurich)
Olga Sorkine-Hornung (ETH Zurich)
In this example, we edited the upper left image and added ivy on the wall, additional windows, and cracks in the building (bottom left). These edits are then automatically propagated to a collection of images of the same object taken from different perspectives and orientations.
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 viewpoint, 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.
The documents contained in these directories are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.