A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2015

AUTHORS

Radu Timofte , Vincent De Smet , Luc Van Gool

ABSTRACT

We address the problem of image upscaling in the form of single image super-resolution based on a dictionary of low- and high-resolution exemplars. Two recently proposed methods, Anchored Neighborhood Regression (ANR) and Simple Functions (SF), provide state-of-the-art quality performance. Moreover, ANR is among the fastest known super-resolution methods. ANR learns sparse dictionaries and regressors anchored to the dictionary atoms. SF relies on clusters and corresponding learned functions. We propose A+, an improved variant of ANR, which combines the best qualities of ANR and SF. A+ builds on the features and anchored regressors from ANR but instead of learning the regressors on the dictionary it uses the full training material, similar to SF. We validate our method on standard images and compare with state-of-the-art methods. We obtain improved quality (i.e. 0.2–0.7 dB PSNR better than ANR) and excellent time complexity, rendering A+ the most efficient dictionary-based super-resolution method to date. More... »

PAGES

111-126

References to SciGraph publications

  • 2012. On Single Image Scale-Up Using Sparse-Representations in CURVES AND SURFACES
  • 2014. Learning a Deep Convolutional Network for Image Super-Resolution in COMPUTER VISION – ECCV 2014
  • 2000-10. Learning Low-Level Vision in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • Book

    TITLE

    Computer Vision -- ACCV 2014

    ISBN

    978-3-319-16816-6
    978-3-319-16817-3

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-319-16817-3_8

    DOI

    http://dx.doi.org/10.1007/978-3-319-16817-3_8

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1040555336


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Swiss Federal Institute of Technology in Zurich", 
              "id": "https://www.grid.ac/institutes/grid.5801.c", 
              "name": [
                "CVL, D-ITET, ETH Z\u00fcrich, Z\u00fcrich, Switzerland"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Timofte", 
            "givenName": "Radu", 
            "id": "sg:person.015566156110.72", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015566156110.72"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "KU Leuven", 
              "id": "https://www.grid.ac/institutes/grid.5596.f", 
              "name": [
                "VISICS, ESAT/PSI, KU Leuven, Leuven, Belgium"
              ], 
              "type": "Organization"
            }, 
            "familyName": "De Smet", 
            "givenName": "Vincent", 
            "id": "sg:person.011446167006.17", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011446167006.17"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Swiss Federal Institute of Technology in Zurich", 
              "id": "https://www.grid.ac/institutes/grid.5801.c", 
              "name": [
                "CVL, D-ITET, ETH Z\u00fcrich, Z\u00fcrich, Switzerland"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Van Gool", 
            "givenName": "Luc", 
            "id": "sg:person.012466346373.62", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012466346373.62"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1023/a:1026501619075", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1006755345", 
              "https://doi.org/10.1023/a:1026501619075"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tip.2010.2050625", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019629051"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-10593-2_13", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022837810", 
              "https://doi.org/10.1007/978-3-319-10593-2_13"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patrec.2013.08.010", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041035321"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-27413-8_47", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046665234", 
              "https://doi.org/10.1007/978-3-642-27413-8_47"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1126/science.290.5500.2323", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1051806676"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2010.5540206", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093215698"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2008.4587647", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093279302"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2009.5459271", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093345646"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2013.241", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093754462"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2013.121", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093814881"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2013.352", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094566218"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2008.4587659", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095062640"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2001.937655", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095756716"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.5244/c.26.135", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099383173"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2015", 
        "datePublishedReg": "2015-01-01", 
        "description": "We address the problem of image upscaling in the form of single image super-resolution based on a dictionary of low- and high-resolution exemplars. Two recently proposed methods, Anchored Neighborhood Regression (ANR) and Simple Functions (SF), provide state-of-the-art quality performance. Moreover, ANR is among the fastest known super-resolution methods. ANR learns sparse dictionaries and regressors anchored to the dictionary atoms. SF relies on clusters and corresponding learned functions. We propose A+, an improved variant of ANR, which combines the best qualities of ANR and SF. A+ builds on the features and anchored regressors from ANR but instead of learning the regressors on the dictionary it uses the full training material, similar to SF. We validate our method on standard images and compare with state-of-the-art methods. We obtain improved quality (i.e. 0.2\u20130.7\u00a0dB PSNR better than ANR) and excellent time complexity, rendering A+ the most efficient dictionary-based super-resolution method to date.", 
        "editor": [
          {
            "familyName": "Cremers", 
            "givenName": "Daniel", 
            "type": "Person"
          }, 
          {
            "familyName": "Reid", 
            "givenName": "Ian", 
            "type": "Person"
          }, 
          {
            "familyName": "Saito", 
            "givenName": "Hideo", 
            "type": "Person"
          }, 
          {
            "familyName": "Yang", 
            "givenName": "Ming-Hsuan", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-319-16817-3_8", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": {
          "isbn": [
            "978-3-319-16816-6", 
            "978-3-319-16817-3"
          ], 
          "name": "Computer Vision -- ACCV 2014", 
          "type": "Book"
        }, 
        "name": "A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution", 
        "pagination": "111-126", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-319-16817-3_8"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "c130c37422e9982fb76f292ecac426a2e3ea13d3863d852f3985cfb7c00fc235"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1040555336"
            ]
          }
        ], 
        "publisher": {
          "location": "Cham", 
          "name": "Springer International Publishing", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-319-16817-3_8", 
          "https://app.dimensions.ai/details/publication/pub.1040555336"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-15T14:27", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8669_00000268.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/978-3-319-16817-3_8"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-16817-3_8'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-16817-3_8'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-16817-3_8'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-16817-3_8'


     

    This table displays all metadata directly associated to this object as RDF triples.

    145 TRIPLES      23 PREDICATES      42 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-319-16817-3_8 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nd9b5064dca214f76b7709b282d16bb50
    4 schema:citation sg:pub.10.1007/978-3-319-10593-2_13
    5 sg:pub.10.1007/978-3-642-27413-8_47
    6 sg:pub.10.1023/a:1026501619075
    7 https://doi.org/10.1016/j.patrec.2013.08.010
    8 https://doi.org/10.1109/cvpr.2008.4587647
    9 https://doi.org/10.1109/cvpr.2008.4587659
    10 https://doi.org/10.1109/cvpr.2010.5540206
    11 https://doi.org/10.1109/iccv.2001.937655
    12 https://doi.org/10.1109/iccv.2009.5459271
    13 https://doi.org/10.1109/iccv.2013.121
    14 https://doi.org/10.1109/iccv.2013.241
    15 https://doi.org/10.1109/iccv.2013.352
    16 https://doi.org/10.1109/tip.2010.2050625
    17 https://doi.org/10.1126/science.290.5500.2323
    18 https://doi.org/10.5244/c.26.135
    19 schema:datePublished 2015
    20 schema:datePublishedReg 2015-01-01
    21 schema:description We address the problem of image upscaling in the form of single image super-resolution based on a dictionary of low- and high-resolution exemplars. Two recently proposed methods, Anchored Neighborhood Regression (ANR) and Simple Functions (SF), provide state-of-the-art quality performance. Moreover, ANR is among the fastest known super-resolution methods. ANR learns sparse dictionaries and regressors anchored to the dictionary atoms. SF relies on clusters and corresponding learned functions. We propose A+, an improved variant of ANR, which combines the best qualities of ANR and SF. A+ builds on the features and anchored regressors from ANR but instead of learning the regressors on the dictionary it uses the full training material, similar to SF. We validate our method on standard images and compare with state-of-the-art methods. We obtain improved quality (i.e. 0.2–0.7 dB PSNR better than ANR) and excellent time complexity, rendering A+ the most efficient dictionary-based super-resolution method to date.
    22 schema:editor N779864a4d068472089f4b0eb54338110
    23 schema:genre chapter
    24 schema:inLanguage en
    25 schema:isAccessibleForFree false
    26 schema:isPartOf N4874afba749b4d2294c2d8353094835e
    27 schema:name A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution
    28 schema:pagination 111-126
    29 schema:productId N3f92a43577c94849bf5f7d60dd07b47c
    30 N9fdb941b0b36400996041100c697df45
    31 Nd5054cacaf6a47f18172d0e81ed4878a
    32 schema:publisher N03b28317317749e284f583ef430e1ffa
    33 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040555336
    34 https://doi.org/10.1007/978-3-319-16817-3_8
    35 schema:sdDatePublished 2019-04-15T14:27
    36 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    37 schema:sdPublisher N1a7df2194b6c444db1da3993ac440575
    38 schema:url http://link.springer.com/10.1007/978-3-319-16817-3_8
    39 sgo:license sg:explorer/license/
    40 sgo:sdDataset chapters
    41 rdf:type schema:Chapter
    42 N03b28317317749e284f583ef430e1ffa schema:location Cham
    43 schema:name Springer International Publishing
    44 rdf:type schema:Organisation
    45 N0cb05478f5264b5da8932b2302cffb31 schema:familyName Cremers
    46 schema:givenName Daniel
    47 rdf:type schema:Person
    48 N117a332463354118960264d813cb7397 rdf:first Nf9dd1be80e404b11a0a3f2f829739611
    49 rdf:rest Nc9dadaf7c66c4342a95f71273aeeff9c
    50 N1292116b75c944698036501e107ad89e rdf:first sg:person.011446167006.17
    51 rdf:rest N99026286aeca431d8c7f504a0ee51e6a
    52 N1a7df2194b6c444db1da3993ac440575 schema:name Springer Nature - SN SciGraph project
    53 rdf:type schema:Organization
    54 N31d681cf86634fd19bd0de0e99246d3d rdf:first Nceb69022555c40fa9f17a2c75c5a5b35
    55 rdf:rest N117a332463354118960264d813cb7397
    56 N3f92a43577c94849bf5f7d60dd07b47c schema:name readcube_id
    57 schema:value c130c37422e9982fb76f292ecac426a2e3ea13d3863d852f3985cfb7c00fc235
    58 rdf:type schema:PropertyValue
    59 N4874afba749b4d2294c2d8353094835e schema:isbn 978-3-319-16816-6
    60 978-3-319-16817-3
    61 schema:name Computer Vision -- ACCV 2014
    62 rdf:type schema:Book
    63 N779864a4d068472089f4b0eb54338110 rdf:first N0cb05478f5264b5da8932b2302cffb31
    64 rdf:rest N31d681cf86634fd19bd0de0e99246d3d
    65 N99026286aeca431d8c7f504a0ee51e6a rdf:first sg:person.012466346373.62
    66 rdf:rest rdf:nil
    67 N9fdb941b0b36400996041100c697df45 schema:name doi
    68 schema:value 10.1007/978-3-319-16817-3_8
    69 rdf:type schema:PropertyValue
    70 Nbaf95c578dcd42c78d17005e81d58bc0 schema:familyName Yang
    71 schema:givenName Ming-Hsuan
    72 rdf:type schema:Person
    73 Nc9dadaf7c66c4342a95f71273aeeff9c rdf:first Nbaf95c578dcd42c78d17005e81d58bc0
    74 rdf:rest rdf:nil
    75 Nceb69022555c40fa9f17a2c75c5a5b35 schema:familyName Reid
    76 schema:givenName Ian
    77 rdf:type schema:Person
    78 Nd5054cacaf6a47f18172d0e81ed4878a schema:name dimensions_id
    79 schema:value pub.1040555336
    80 rdf:type schema:PropertyValue
    81 Nd9b5064dca214f76b7709b282d16bb50 rdf:first sg:person.015566156110.72
    82 rdf:rest N1292116b75c944698036501e107ad89e
    83 Nf9dd1be80e404b11a0a3f2f829739611 schema:familyName Saito
    84 schema:givenName Hideo
    85 rdf:type schema:Person
    86 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    87 schema:name Information and Computing Sciences
    88 rdf:type schema:DefinedTerm
    89 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    90 schema:name Artificial Intelligence and Image Processing
    91 rdf:type schema:DefinedTerm
    92 sg:person.011446167006.17 schema:affiliation https://www.grid.ac/institutes/grid.5596.f
    93 schema:familyName De Smet
    94 schema:givenName Vincent
    95 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011446167006.17
    96 rdf:type schema:Person
    97 sg:person.012466346373.62 schema:affiliation https://www.grid.ac/institutes/grid.5801.c
    98 schema:familyName Van Gool
    99 schema:givenName Luc
    100 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012466346373.62
    101 rdf:type schema:Person
    102 sg:person.015566156110.72 schema:affiliation https://www.grid.ac/institutes/grid.5801.c
    103 schema:familyName Timofte
    104 schema:givenName Radu
    105 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015566156110.72
    106 rdf:type schema:Person
    107 sg:pub.10.1007/978-3-319-10593-2_13 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022837810
    108 https://doi.org/10.1007/978-3-319-10593-2_13
    109 rdf:type schema:CreativeWork
    110 sg:pub.10.1007/978-3-642-27413-8_47 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046665234
    111 https://doi.org/10.1007/978-3-642-27413-8_47
    112 rdf:type schema:CreativeWork
    113 sg:pub.10.1023/a:1026501619075 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006755345
    114 https://doi.org/10.1023/a:1026501619075
    115 rdf:type schema:CreativeWork
    116 https://doi.org/10.1016/j.patrec.2013.08.010 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041035321
    117 rdf:type schema:CreativeWork
    118 https://doi.org/10.1109/cvpr.2008.4587647 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093279302
    119 rdf:type schema:CreativeWork
    120 https://doi.org/10.1109/cvpr.2008.4587659 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095062640
    121 rdf:type schema:CreativeWork
    122 https://doi.org/10.1109/cvpr.2010.5540206 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093215698
    123 rdf:type schema:CreativeWork
    124 https://doi.org/10.1109/iccv.2001.937655 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095756716
    125 rdf:type schema:CreativeWork
    126 https://doi.org/10.1109/iccv.2009.5459271 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093345646
    127 rdf:type schema:CreativeWork
    128 https://doi.org/10.1109/iccv.2013.121 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093814881
    129 rdf:type schema:CreativeWork
    130 https://doi.org/10.1109/iccv.2013.241 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093754462
    131 rdf:type schema:CreativeWork
    132 https://doi.org/10.1109/iccv.2013.352 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094566218
    133 rdf:type schema:CreativeWork
    134 https://doi.org/10.1109/tip.2010.2050625 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019629051
    135 rdf:type schema:CreativeWork
    136 https://doi.org/10.1126/science.290.5500.2323 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051806676
    137 rdf:type schema:CreativeWork
    138 https://doi.org/10.5244/c.26.135 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099383173
    139 rdf:type schema:CreativeWork
    140 https://www.grid.ac/institutes/grid.5596.f schema:alternateName KU Leuven
    141 schema:name VISICS, ESAT/PSI, KU Leuven, Leuven, Belgium
    142 rdf:type schema:Organization
    143 https://www.grid.ac/institutes/grid.5801.c schema:alternateName Swiss Federal Institute of Technology in Zurich
    144 schema:name CVL, D-ITET, ETH Zürich, Zürich, Switzerland
    145 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...