Patch Based Synthesis for Single Depth Image Super-Resolution

Oisin Mac Aodha, Neill D.F. Campbell, Arun Nair, Gabriel J. Brostow

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

We present an algorithm to synthetically increase the resolution of a solitary depth image using only a generic database of local patches. Modern range sensors measure depths with non-Gaussian noise and at lower starting resolutions than typical visible-light cameras. While patch based approaches for upsampling intensity images continue to improve, this is the first exploration of patching for depth images.
We match against the height field of each low resolution input depth patch, and search our database for a list of appropriate high resolution candidate patches. Selecting the right candidate at each location in the depth image is then posed as a Markov random field labeling problem. Our experiments also show how important further depth-specific processing, such as noise removal and correct patch normalization, dramatically improves our results. Perhaps surprisingly, even better results are achieved on a variety of real test scenes by providing our algorithm with only synthetic training depth data.
Original languageEnglish
Title of host publicationComputer Vision -- ECCV 2012
EditorsAndrew Fitzgibbon, Svetlana Lazebnik, Pietro Perona, Yoichi Sato, Cordelia Schmid
Place of PublicationBerlin, Heidelberg
PublisherSpringer Berlin Heidelberg
Number of pages14
ISBN (Electronic)978-3-642-33712-3
ISBN (Print)978-3-642-33712-3
Publication statusPublished - 13 Oct 2012
Event12th European Conference on Computer Vision - Firenze, Italy
Duration: 7 Oct 201213 Oct 2012

Publication series

NameLecture Notes in Computer Science (LNCS)
PublisherSpringer, Berlin, Heidelberg
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference12th European Conference on Computer Vision
Abbreviated titleECCV 2012
Internet address


Dive into the research topics of 'Patch Based Synthesis for Single Depth Image Super-Resolution'. Together they form a unique fingerprint.

Cite this