Hallucinating multiple occluded face images of different resolutions

Authors:
Kui Jia;Shaogang Gong
Affiliations:
Department of Computer Science, Queen Mary University of London, Mile End Road, London E1 4NS, UK;Department of Computer Science, Queen Mary University of London, Mile End Road, London E1 4NS, UK
Venue:
Pattern Recognition Letters
Year:
2006

Citing 8
Cited 3

Improving resolution by image registration

CVGIP: Graphical Models and Image Processing
A non-parametric multi-scale statistical model for natural images

NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
Hallucinating Faces

FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Learning Low-Level Vision

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
High-zoom video hallucination by exploiting spatio-temporal regularities

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Extraction of high-resolution frames from video sequences

IEEE Transactions on Image Processing
Joint MAP registration and high-resolution image estimation using a sequence of undersampled images

IEEE Transactions on Image Processing
Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images

IEEE Transactions on Image Processing

Frontal face generation from multiple low-resolution non-frontal faces for face recognition

ACCV'10 Proceedings of the 2010 international conference on Computer vision - Volume Part I
Eigentransformation-based face super-resolution in the wavelet domain

Pattern Recognition Letters
HEASK: Robust homography estimation based on appearance similarity and keypoint correspondences

Pattern Recognition

Quantified Score

Hi-index	0.10

Visualization

Abstract

Learning-based super-resolution has recently been proposed for enhancing human face images, known as ''face hallucination''. In this paper, we propose a novel algorithm to super-resolve face images given multiple partially occluded inputs at different lower resolutions. By integrating hierarchical patch-wise alignment and inter-frame constraints into a Bayesian framework, we can probabilistically align multiple input images at different resolutions and recursively infer the high-resolution face image. We address the problem of fusing partial imagery information through multiple frames and discuss the new algorithm's effectiveness when encountering occluded low-resolution face images. We show promising results compared to those of existing face hallucination methods from both simulated facial database and live video sequences.