We propose a system to restrict the manipulation of shape and appearance in an image to a valid subspace which we learn from a collection of exemplar images. To this end, we automatically co-align a collection of images and learn a subspace model of shape and appearance using principal components. As finding perfect image correspondences for general images is not feasible, we build an approximate partial alignment and improve bad alignments leveraging other, more successful alignments. Our system allows the user to change appearance and shape in real-time and the result is ``projected'' onto the subspace of meaningful changes. The change in appearance and shape can either be locked or performed independently. Additional applications include suggestion of alternative shapes or appearance.
|
Data-driven Color Manifolds
Chuong H. Nguyen, Tobias Ritschel, Hans-Peter Seidel ACM Transactions on Graphics 34(2), 2015.
|
Chuong H. Nguyen, Oliver Nalbach, Tobias Ritschel, Hans-Peter Seidel
Guiding Image Manipulations using Shape-appearance Subspaces from Co-alignment of Image Collections
Computer Graphics Forum 34(2) (Proc. Eurographics, Zürich/Switzerland, 4th – 8th May 2015)
@article{NguyenEG2015,
author = {Chuong H. Nguyen and Oliver Nalbach and Tobias Ritschel and Hans-Peter Seidel},
title = {Guiding Image Manipulations using Shape-appearance Subspaces from Co-alignment of Image Collections},
journal = {Computer Graphics Forum (Proc. Eurographics 2015)},
year = {2015},
volume = {34},
number = {2}}
Computer Graphics Forum © 2015 The Eurographics Association and Blackwell Publishing Ltd. Published by Blackwell Publishing, 9600 Garsington Road, Oxford OX4 2DQ, UK and 350 Main Street, Malden, MA 02148, USA.
This is the author's version of the work. It is posted here by permission of EUROGRAPHICS / Blackwell Publishing for your personal use. Not for redistribution.
.