2010 | OriginalPaper | Buchkapitel
Interactive Super-Resolution through Neighbor Embedding
verfasst von : Jian Pu, Junping Zhang, Peihong Guo, Xiaoru Yuan
Erschienen in: Computer Vision – ACCV 2009
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Learning based super-resolution can recover high resolution image with high quality. However, building an interactive learning based super-resolution system for general images is extremely challenging. In this paper, we proposed a novel GPU-based
I
nteractive
S
uper-
R
esolution system through
N
eighbor
E
mbedding (
ISRNE
). Random projection tree (
RPtree
) with manifold sampling is employed to reduce the number of redundant image patches and balance the node size of the tree. Significant performance improvement is achieved through the incorporation of a refined GPU-based brute force
kNN
search with a matrix-multiplication-like technique. We demonstrate 200-300 times speedup of our proposed
ISRNE
system with experiments in both small size and large size images.