A multiresolution spline with application to image mosaics
ACM Transactions on Graphics (TOG)
Computer facial animation
Linear Object Classes and Image Synthesis From a Single Example Image
IEEE Transactions on Pattern Analysis and Machine Intelligence
Painterly rendering with curved brush strokes of multiple sizes
Proceedings of the 25th annual conference on Computer graphics and interactive techniques
A morphable model for the synthesis of 3D faces
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
Putting social sciences together again: an introduction to the volume
Dynamics in human and primate societies
Analysis and Synthesis of Facial Image Sequences Using Physical and Anatomical Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition Based on Fitting a 3D Morphable Model
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Face transfer with multilinear models
ACM SIGGRAPH 2005 Papers
Line drawings from volume data
ACM SIGGRAPH 2005 Papers
Creating face models from vague mental images
SIGGRAPH '05 ACM SIGGRAPH 2005 Sketches
| Hi-index | 0.00 |
This paper describes a system for animation and modeling of faces in images or in 3D. It provides high-level control of facial appearance to users, due to a learning-based approach that extracts class-specific information from a database of 3D scans. The modification tools include changes of facial attributes, such as body weight, masculine or feminine look, or overall head shape. Facial expressions are learned from examples and can be applied to new individuals. The system is intrinsically based on 3D face shapes and surface colors, but it can be applied to existing images as well, using a 3D shape reconstruction algorithm that operates on single images. After reconstruction, faces can be modified and drawn back into the original image, so the users can manipulate, animate and exchange faces in images at any given pose and illumination. The system can be used to create face models or images from a vague description or mental image, for example based on the recollection of eyewitnesses in forensic applications. For this specific problem, we present a software tool and a user study with a forensic artist. Our model-based approach may be considered a prototype implementation of a high-level user interface to control meaningful attributes in human faces.