Motion compensated video super resolution

Authors:
Sune Høgild Keller;François Lauze;Mads Nielsen
Affiliations:
The Image Group, Department of Computer Science, University of Copenhagen, Copenhagen, Denmark;Nordic Bioscience A/S, Herlev, Denmark;The Image Group, Department of Computer Science, University of Copenhagen, Copenhagen, Denmark and Nordic Bioscience A/S, Herlev, Denmark
Venue:
SSVM'07 Proceedings of the 1st international conference on Scale space and variational methods in computer vision
Year:
2007

Citing 11
Cited 1

Scale-Space and Edge Detection Using Anisotropic Diffusion

IEEE Transactions on Pattern Analysis and Machine Intelligence
Super-Resolution Imaging

Super-Resolution Imaging
Limits on Super-Resolution and How to Break Them

IEEE Transactions on Pattern Analysis and Machine Intelligence
Feature-Based Image Analysis

International Journal of Computer Vision
Fundamental Limits of Reconstruction-Based Superresolution Algorithms under Local Translation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods

International Journal of Computer Vision
Space-Time Super-Resolution

IEEE Transactions on Pattern Analysis and Machine Intelligence
Simultaneous inpainting and motion estimation of highly degraded video-sequences

SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
Extraction of high-resolution frames from video sequences

IEEE Transactions on Image Processing
Fast and robust multiframe super resolution

IEEE Transactions on Image Processing
Variational optical flow computation in real time

IEEE Transactions on Image Processing

A Scale-Space Approach to Landmark Constrained Image Registration

SSVM '09 Proceedings of the Second International Conference on Scale Space and Variational Methods in Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a variational, spatiotemporal video super resolution scheme that produces not just one but n high resolution video frames from an n frame low resolution video sequence. We use a generic prior and the output is artifact-free, sharp and superior in quality to state of the art home cinema video processors. Unlike many other super resolution schemes, ours does not limit itself to just translational or affine motion, or to certain subclasses of image content to optimize the output quality.We present a link between image reconstruction and super resolution and formulate our super resolution constraint with arbitrary up-scaling factors in space from that.