Technical Papers

By-Example Image Synthesis

Tuesday, 9 August 3:45 pm - 5:15 pm | East Building, Ballroom C
Session Chair: Dan Goldman, Adobe Systems Incorporated

Expression Flow for 3D-Aware Face Component Transfer

This paper addresses the problem of transferring facial components between images with different expressions. Expression Flow is a 2D flow field that warps the target face globally so that the warped face becomes compatible with the new feature to be blended in.

Fei Yang
Rutgers University

Jue Wang
Adobe Systems Incorporated

Eli Shechtman
Adobe Systems Incorporated

Lubomir Bourdev
University of California, Berkeley

Dimitri Metaxas
Rutgers University

Image-Guided Weathering: A New Approach Applied to Flow Phenomena

With this new technique, weathering data can be extracted from photographs of real scenes and applied to generate similar weathering appearance in new environments. Stains produced by fluid flow illustrate a representative case.

Carles Bosch
REVES/INRIA Sophia Antipolis

Pierre-Yves Laffont
REVES/INRIA Sophia Antipolis

Holly Rushmeier
Yale University

Julie Dorsey
Yale University

George Drettakis
REVES/INRIA Sophia Antipolis

Exploring Photobios

A method for generating face animations from large image collections of the same person, by computing an optimized, aligned subsequence. This approach is the basis for the Picasa's Face Movies feature. A key contribution of this paper is proving why the cross dissolve produces a strong motion effect.

Ira Kemelmacher-Shlizerman
University of Washington

Eli Shechtman
Adobe Systems Incorporated

Rahul Garg
University of Washington

Steven M. Seitz
University of Washington

Discrete Element Textures

A data-driven method for synthesizing phenomena characterized by repetitive discrete elements, such as a stack of fresh produce, a plate of noodles, or a mosaic pattern. The method is general and easy to use, requiring only a small input exemplar and a coarse output domain.

Chongyang Ma
Tsinghua University and Microsoft Research Asia

Li-Yi Wei
Microsoft Research

Xin Tong
Microsoft Research Asia