Improving resolution by image registration
CVGIP: Graphical Models and Image Processing
Super-Resolution Reconstruction of Image Sequences
IEEE Transactions on Pattern Analysis and Machine Intelligence
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
Efficient and reliable schemes for nonlinear diffusion filtering
IEEE Transactions on Image Processing
Superresolution restoration of an image sequence: adaptive filtering approach
IEEE Transactions on Image Processing
Guest Editorial: Generative model based vision
Computer Vision and Image Understanding
On the computational rationale for generative models
Computer Vision and Image Understanding
A Superresolution Framework for High-Accuracy Multiview Reconstruction
Proceedings of the 31st DAGM Symposium on Pattern Recognition
GPU-accelerated hierarchical dense correspondence for real-time aerial video processing
WMVC'09 Proceedings of the 2009 international conference on Motion and video computing
Matte super-resolution for compositing
Proceedings of the 32nd DAGM conference on Pattern recognition
Improving sub-pixel correspondence through upsampling
Computer Vision and Image Understanding
Asynchronous frameless event-based optical flow
Neural Networks
Accurate image registration for MAP image super-resolution
Image Communication
A Super-Resolution Framework for High-Accuracy Multiview Reconstruction
International Journal of Computer Vision
Hi-index | 0.00 |
This paper deals with the computation of a single super-resolution image from a set of low-resolution images, where the motion fields are not constrained to be parametric. In our approach, the inversion process, in which the super-resolved image is inferred from the input data, is interleaved with the computation of a set of dense optical flow fields. The case of arbitrary motion presents several significant challenges. First of all, the super-resolution setting dictates that the optic flow computations must be very precise. Furthermore, we have to consider the possibility that certain parts of the scene, which are visible in the super-resolved image, are occluded in some of the input images. Such occlusions must be identified and dealt with in the restoration process. We propose a Bayesian approach to tackle these problems. In this framework, the input images are regarded as sub-sampled and noisy versions of the unknown high-quality image. Also, the input data is considered incomplete, in the sense that we do not know which pixels from the evolving super-resolution image are occluded in particular images from the input set. This will be modelled by introducing so-called visibility maps, which are treated as hidden variables. We describe an Expectation-Maximisation (EM) algorithm, which iterates between estimating values for the hidden quantities, and optimising the flow-fields and the super-resolution image. The approach is illustrated with a synthetic and two challenging real-world examples.