Method and an apparatus for generating an Approximate Nearest Neighbor Field (ANNF) for images and video sequences

Method and an apparatus for generating an Approximate Nearest Neighbor Field (ANNF) for images and video sequences

An algorithm for performing super-resolution splits an input image or video into patches and relies on image self-similarity, wherein similar patches are searched in different downscaled versions of an image, using Approximate Nearest-Neighbor Fields (ANNF). The goal of ANNF is to locate with a mini...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: SALVADOR MARCOS, JORDI, BAGCILAR, MELIKE, KOCHALE, AXEL
Format: Patent
Sprache:eng ; fre ; ger
Schlagworte:
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator SALVADOR MARCOS, JORDI
BAGCILAR, MELIKE
KOCHALE, AXEL
description An algorithm for performing super-resolution splits an input image or video into patches and relies on image self-similarity, wherein similar patches are searched in different downscaled versions of an image, using Approximate Nearest-Neighbor Fields (ANNF). The goal of ANNF is to locate with a minimal number of search iterations for each patch of a source image the k most similar patches in a downscaled version of the source image or video. A method for generating an ANNF for images of an input video (15) comprises generating (20) a plurality of downscaled versions of the images of the input video at different scales, generating (30) an Inverse ANNF (IANNF) for the input video by finding for each patch of the downscaled images similar patches in the input video, generating (40) an ANNF for the input video by reversing the IANNF, and filling gaps in the ANNF by random search.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP2924648A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP2924648A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP2924648A13</originalsourceid><addsrcrecordid>eNqNjbEOgjAQhlkcjPoON-rgIBKjY2MgLhIHd3LCT2mCbW2L8fEtxAdwuHy5_N_dP0_cFaEzDbEeh9hadhwGT61xJKERN6XlmAlrnfmoJwdQCXbwIVLJ7hHVQqFvaC3KsthMt9GT8NPft2pgyOM1QNfwy2TWcu-x-nGRUJHfz5ctrKngLdexNlT5LT2l2SE7it3-D-ULlJhCKg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Method and an apparatus for generating an Approximate Nearest Neighbor Field (ANNF) for images and video sequences</title><source>esp@cenet</source><creator>SALVADOR MARCOS, JORDI ; BAGCILAR, MELIKE ; KOCHALE, AXEL</creator><creatorcontrib>SALVADOR MARCOS, JORDI ; BAGCILAR, MELIKE ; KOCHALE, AXEL</creatorcontrib><description>An algorithm for performing super-resolution splits an input image or video into patches and relies on image self-similarity, wherein similar patches are searched in different downscaled versions of an image, using Approximate Nearest-Neighbor Fields (ANNF). The goal of ANNF is to locate with a minimal number of search iterations for each patch of a source image the k most similar patches in a downscaled version of the source image or video. A method for generating an ANNF for images of an input video (15) comprises generating (20) a plurality of downscaled versions of the images of the input video at different scales, generating (30) an Inverse ANNF (IANNF) for the input video by finding for each patch of the downscaled images similar patches in the input video, generating (40) an ANNF for the input video by reversing the IANNF, and filling gaps in the ANNF by random search.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2015</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20150930&amp;DB=EPODOC&amp;CC=EP&amp;NR=2924648A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,778,883,25547,76298</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20150930&amp;DB=EPODOC&amp;CC=EP&amp;NR=2924648A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SALVADOR MARCOS, JORDI</creatorcontrib><creatorcontrib>BAGCILAR, MELIKE</creatorcontrib><creatorcontrib>KOCHALE, AXEL</creatorcontrib><title>Method and an apparatus for generating an Approximate Nearest Neighbor Field (ANNF) for images and video sequences</title><description>An algorithm for performing super-resolution splits an input image or video into patches and relies on image self-similarity, wherein similar patches are searched in different downscaled versions of an image, using Approximate Nearest-Neighbor Fields (ANNF). The goal of ANNF is to locate with a minimal number of search iterations for each patch of a source image the k most similar patches in a downscaled version of the source image or video. A method for generating an ANNF for images of an input video (15) comprises generating (20) a plurality of downscaled versions of the images of the input video at different scales, generating (30) an Inverse ANNF (IANNF) for the input video by finding for each patch of the downscaled images similar patches in the input video, generating (40) an ANNF for the input video by reversing the IANNF, and filling gaps in the ANNF by random search.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2015</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjbEOgjAQhlkcjPoON-rgIBKjY2MgLhIHd3LCT2mCbW2L8fEtxAdwuHy5_N_dP0_cFaEzDbEeh9hadhwGT61xJKERN6XlmAlrnfmoJwdQCXbwIVLJ7hHVQqFvaC3KsthMt9GT8NPft2pgyOM1QNfwy2TWcu-x-nGRUJHfz5ctrKngLdexNlT5LT2l2SE7it3-D-ULlJhCKg</recordid><startdate>20150930</startdate><enddate>20150930</enddate><creator>SALVADOR MARCOS, JORDI</creator><creator>BAGCILAR, MELIKE</creator><creator>KOCHALE, AXEL</creator><scope>EVB</scope></search><sort><creationdate>20150930</creationdate><title>Method and an apparatus for generating an Approximate Nearest Neighbor Field (ANNF) for images and video sequences</title><author>SALVADOR MARCOS, JORDI ; BAGCILAR, MELIKE ; KOCHALE, AXEL</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP2924648A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2015</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>SALVADOR MARCOS, JORDI</creatorcontrib><creatorcontrib>BAGCILAR, MELIKE</creatorcontrib><creatorcontrib>KOCHALE, AXEL</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SALVADOR MARCOS, JORDI</au><au>BAGCILAR, MELIKE</au><au>KOCHALE, AXEL</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Method and an apparatus for generating an Approximate Nearest Neighbor Field (ANNF) for images and video sequences</title><date>2015-09-30</date><risdate>2015</risdate><abstract>An algorithm for performing super-resolution splits an input image or video into patches and relies on image self-similarity, wherein similar patches are searched in different downscaled versions of an image, using Approximate Nearest-Neighbor Fields (ANNF). The goal of ANNF is to locate with a minimal number of search iterations for each patch of a source image the k most similar patches in a downscaled version of the source image or video. A method for generating an ANNF for images of an input video (15) comprises generating (20) a plurality of downscaled versions of the images of the input video at different scales, generating (30) an Inverse ANNF (IANNF) for the input video by finding for each patch of the downscaled images similar patches in the input video, generating (40) an ANNF for the input video by reversing the IANNF, and filling gaps in the ANNF by random search.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP2924648A1
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title Method and an apparatus for generating an Approximate Nearest Neighbor Field (ANNF) for images and video sequences
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T02%3A31%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=SALVADOR%20MARCOS,%20JORDI&rft.date=2015-09-30&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP2924648A1%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true