Neighbor embedding based super-resolution algorithm through edge detection and feature selection
Pattern Recognition Letters
ICIAP '09 Proceedings of the 15th International Conference on Image Analysis and Processing
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
Face hallucination with shape parameters projection constraint
Proceedings of the international conference on Multimedia
Subspace-based holistic registration for low-resolution facial images
EURASIP Journal on Advances in Signal Processing
Locally affine patch mapping and global refinement for image super-resolution
Pattern Recognition
A survey of face hallucination
CCBR'12 Proceedings of the 7th Chinese conference on Biometric Recognition
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II
Face hallucination on personal photo albums
ACCV'12 Proceedings of the 11th international conference on Computer Vision - Volume 2
Feature-domain super-resolution for iris recognition
Computer Vision and Image Understanding
A Comprehensive Survey to Face Hallucination
International Journal of Computer Vision
Low-resolution face recognition: a review
The Visual Computer: International Journal of Computer Graphics
| Hi-index | 0.01 |
Existing learning-based face super-resolution (hallucination) techniques generate high-resolution images of a single facial modality (i.e., at a fixed expression, pose and illumination) given one or set of low-resolution face images as probe. Here, we present a generalized approach based on a hierarchical tensor (multilinear) space representation for hallucinating high-resolution face images across multiple modalities, achieving generalization to variations in expression and pose. In particular, we formulate a unified tensor which can be reduced to two parts: a global image-based tensor for modeling the mappings among different facial modalities, and a local patch-based multiresolution tensor for incorporating high-resolution image details. For realistic hallucination of unregistered low-resolution faces contained in raw images, we develop an automatic face alignment algorithm capable of pixel-wise alignment by iteratively warping the probing face to its projection in the space of training face images. Our experiments show not only performance superiority over existing benchmark face super-resolution techniques on single modal face hallucination, but also novelty of our approach in coping with multimodal hallucination and its robustness in automatic alignment under practical imaging conditions.