Multidimensional Morphable Models: A Framework for Representing and Matching Object Classes
International Journal of Computer Vision
A morphable model for the synthesis of 3D faces
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
Reconstruction of Partially Damaged Face Images Based on a Morphable Face Model
IEEE Transactions on Pattern Analysis and Machine Intelligence
Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
A Statistical Method for Robust 3D Surface Reconstruction from Sparse Data
3DPVT '04 Proceedings of the 3D Data Processing, Visualization, and Transmission, 2nd International Symposium
A Performance Evaluation of Local Descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence
On the Use of SIFT Features for Face Authentication
CVPRW '06 Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop
Journal of Cognitive Neuroscience
Probabilistic Modeling and Visualization of the Flexibility in Morphable Models
Proceedings of the 13th IMA International Conference on Mathematics of Surfaces XIII
| Hi-index | 0.00 |
The problem we address in this paper is, given a facial image that is partially occluded or damaged by noise, to reconstruct a whole face. A key process for the reconstruction is to obtain the correspondences between the input image and the reference face. We present a method that matches an input image with multiple example images that are generated from a morphable face model. From the matched feature points, shape and texture of the full face are inferred by the non-iterative data completion algorithm. Compared with single matching with the particular "reference face", this multiple matching method increases the robustness of the matching. The experimental results of applying the algorithm to face images that are contaminated by Gaussian noise and those which are partially occluded show that the reconstructed faces are plausible and similar to the original ones.