Limits of Learning-Based Superresolution Algorithms
International Journal of Computer Vision
ICA Based Super-Resolution Face Hallucination and Recognition
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks
A 3-D assisted generative model for facial texture super- resolution
BTAS'09 Proceedings of the 3rd IEEE international conference on Biometrics: Theory, applications and systems
Hallucinating face by position-patch
Pattern Recognition
Super-resolution of human face image using canonical correlation analysis
Pattern Recognition
Facial parts-based face hallucination method
ICISP'10 Proceedings of the 4th international conference on Image and signal processing
Region-based reconstruction for face hallucination
MMM'07 Proceedings of the 13th international conference on Multimedia Modeling - Volume Part I
Video-based facial expression hallucination: a two- level hierarchical fusion approach
ACIVS'06 Proceedings of the 8th international conference on Advanced Concepts For Intelligent Vision Systems
Low-resolution face recognition: a review
The Visual Computer: International Journal of Computer Graphics
| Hi-index | 0.00 |
Face hallucination is to synthesize a high-resolution facial image from a low-resolution input. In this paper, we present a new two-step approach to hallucinating faces motivated by the two-step algorithm of Liu et al. First, a linear relationship between both high-resolution and low-resolution facial images is established by applying PCA on both of them, and the global image, which is similar to the original high-resolution image, is reconstructed under a MAP criterion. Second, a linear model between the residual image (the difference between the original image and the global image) and the low-resolution residual image (the difference between the low-resolution input and the manually down-sampled global image) are built, and, following a MRF prior, the optimal residual image is estimated under a MAP criterion again. Experiments demonstrate that our approach can be applied to yield 4-8 fold super-resolution with high-quality hallucinated results.