Paper Info
Title
Video Super-Resolution Using High Quality Photographs
Abstract
This paper introduces a technique that increases the spatial resolution of a given video. The method is built on the fundamentals of super-resolution techniques that aim to reconstruct high-resolution frames from a low-resolution input sequence. Different than classical super-resolution methods, besides using the information of adjacent frames, we take advantage of several reference high quality (resolution) photographs of the same scene. The method is purely image-based, and does not require depth estimation. The additional information extracted from the reference photographs is used to construct several high resolution seed frames added with a constant step in the initial video sequence. Therefore, the seed frames but also the adjacent low-resolution frames provide important information to define priors that are considered in the probabilistic interpretation of the generative model. The estimated solution is obtained based on a standard maximum a posteriori (MAP) approach. Objective tests on real and synthetic video sequences demonstrate the utility and the benefits of the proposed technique over related methods.
Year
DOI
Venue
2010
10.1109/ICASSP.2010.5495223
2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING
Keywords
Field
DocType
super-resolution, MAP, matching
Iterative reconstruction,Reference frame,Computer vision,Pattern recognition,Computer science,Motion compensation,Pixel,Artificial intelligence,Maximum a posteriori estimation,Probabilistic logic,Image resolution,Generative model
Conference
ISSN
Citations 
PageRank 
1520-6149
7
0.50
References 
Authors
7
3
Name
Order
Citations
PageRank
Cosmin Ancuti131422.39
Codruta Orniana Ancuti230420.86
Philippe Bekaert375867.00