Image Metamorphosis with Scattered Feature Constraints
IEEE Transactions on Visualization and Computer Graphics
Reconstruction of Partially Damaged Face Images Based on a Morphable Face Model
IEEE Transactions on Pattern Analysis and Machine Intelligence
ACM SIGGRAPH 2003 Papers
Interactive digital photomontage
ACM SIGGRAPH 2004 Papers
A Nonlinear Approach for Face Sketch Synthesis and Recognition
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Efficient Shape Matching Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image deformation using moving least squares
ACM SIGGRAPH 2006 Papers
Scene completion using millions of photographs
ACM SIGGRAPH 2007 papers
Sketching reality: Realistic interpretation of architectural designs
ACM Transactions on Graphics (TOG)
Data-driven enhancement of facial attractiveness
ACM SIGGRAPH 2008 papers
Face swapping: automatically replacing faces in photographs
ACM SIGGRAPH 2008 papers
Hi-index | 0.00 |
People usually visualize their imaginations or memories through sketching. However, it might be difficult to record color and texture details powered by a large database of photographs gathered from the Web. This paper deals with the imagination visualization problem for human faces. A framework for synthesizing lifelike portraits from user specifications and input sketches is proposed which is an inverse process of sketch generation. The proposed framework synthesizes the realistic appearance of a face by taking parts from an annotated face library of photographs and stitching them together followed by further deformation. The algorithm consists of three parts primarily: First, given user specifications and an input sketch, search good matches for each facial component in the library; Second, extract each facial component from matching source images and composite them together; Third, deform the synthesized lifelike portraits to further approximate the sketch. The key component lies in a measurement for finding the right contents to bridge the gap between shapes and lifelike images. A set of diverse lifelike portraits can be synthesized from a single sketch. The effectiveness of the proposed approach is demonstrated with a variety of experimental results.