Mutual-Structure for Joint Filtering View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2017-06-03

AUTHORS

Xiaoyong Shen, Chao Zhou, Li Xu, Jiaya Jia

ABSTRACT

Previous joint/guided filters directly transfer structural information from the reference to the target image. In this paper, we analyze the major drawback—that is, there may be completely different edges in the two images. Simply considering all patterns could introduce significant errors. To address this issue, we propose the concept of mutual-structure, which refers to the structural information that is contained in both images and thus can be safely enhanced by joint filtering. We also use an untraditional objective function that can be efficiently optimized to yield mutual structure. Our method results in important edge preserving property, which greatly benefits depth completion, optical flow estimation, image enhancement, stereo matching, to name a few. More... »

PAGES

19-33

References to SciGraph publications

  • 2006. Bilateral Filtering-Based Optical Flow Estimation with Occlusion Detection in COMPUTER VISION – ECCV 2006
  • 2010. Guided Image Filtering in COMPUTER VISION – ECCV 2010
  • 2014. Multi-modal and Multi-spectral Registration for Natural Images in COMPUTER VISION – ECCV 2014
  • 2002-04. A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2006. A Fast Approximation of the Bilateral Filter Using a Signal Processing Approach in COMPUTER VISION – ECCV 2006
  • 2012. Recursive Bilateral Filtering in COMPUTER VISION – ECCV 2012
  • 2014. Rolling Guidance Filter in COMPUTER VISION – ECCV 2014
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s11263-017-1021-y

    DOI

    http://dx.doi.org/10.1007/s11263-017-1021-y

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1085762463


    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/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "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"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "The Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, NT, Hong Kong", 
              "id": "http://www.grid.ac/institutes/grid.10784.3a", 
              "name": [
                "The Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, NT, Hong Kong"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Shen", 
            "givenName": "Xiaoyong", 
            "id": "sg:person.016165121117.35", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016165121117.35"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "The Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, NT, Hong Kong", 
              "id": "http://www.grid.ac/institutes/grid.10784.3a", 
              "name": [
                "The Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, NT, Hong Kong"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zhou", 
            "givenName": "Chao", 
            "id": "sg:person.012071567503.69", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012071567503.69"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "SenseTime Group Limited, Shatin, China", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "SenseTime Group Limited, Shatin, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Xu", 
            "givenName": "Li", 
            "id": "sg:person.011131772265.04", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011131772265.04"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "The Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, NT, Hong Kong", 
              "id": "http://www.grid.ac/institutes/grid.10784.3a", 
              "name": [
                "The Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, NT, Hong Kong"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Jia", 
            "givenName": "Jiaya", 
            "id": "sg:person.01005051540.26", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01005051540.26"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-3-642-33718-5_29", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052949246", 
              "https://doi.org/10.1007/978-3-642-33718-5_29"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-15549-9_1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039676932", 
              "https://doi.org/10.1007/978-3-642-15549-9_1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/11744023_17", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1013281471", 
              "https://doi.org/10.1007/11744023_17"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/11744085_44", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009956269", 
              "https://doi.org/10.1007/11744085_44"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-10593-2_21", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009765819", 
              "https://doi.org/10.1007/978-3-319-10593-2_21"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1014573219977", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1004426816", 
              "https://doi.org/10.1023/a:1014573219977"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-10578-9_53", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1018943407", 
              "https://doi.org/10.1007/978-3-319-10578-9_53"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2017-06-03", 
        "datePublishedReg": "2017-06-03", 
        "description": "Previous joint/guided filters directly transfer structural information from the reference to the target image. In this paper, we analyze the major drawback\u2014that is, there may be completely different edges in the two images. Simply considering all patterns could introduce significant errors. To address this issue, we propose the concept of mutual-structure, which refers to the structural information that is contained in both images and thus can be safely enhanced by joint filtering. We also use an untraditional objective function that can be efficiently optimized to yield mutual structure. Our method results in important edge preserving property, which greatly benefits depth completion, optical flow estimation, image enhancement, stereo matching, to name a few.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s11263-017-1021-y", 
        "isAccessibleForFree": false, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.7432685", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": [
          {
            "id": "sg:journal.1032807", 
            "issn": [
              "0920-5691", 
              "1573-1405"
            ], 
            "name": "International Journal of Computer Vision", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1-3", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "125"
          }
        ], 
        "keywords": [
          "joint filtering", 
          "optical flow estimation", 
          "flow estimation", 
          "significant errors", 
          "joint/", 
          "major drawback", 
          "objective function", 
          "stereo matching", 
          "depth completion", 
          "image enhancement", 
          "target image", 
          "filtering", 
          "important edges", 
          "filter", 
          "structural information", 
          "images", 
          "edge", 
          "different edges", 
          "mutual structure", 
          "properties", 
          "drawbacks", 
          "estimation", 
          "information", 
          "enhancement", 
          "error", 
          "structure", 
          "method", 
          "matching", 
          "reference", 
          "issues", 
          "concept", 
          "function", 
          "patterns", 
          "completion", 
          "paper"
        ], 
        "name": "Mutual-Structure for Joint Filtering", 
        "pagination": "19-33", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1085762463"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s11263-017-1021-y"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s11263-017-1021-y", 
          "https://app.dimensions.ai/details/publication/pub.1085762463"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-12-01T06:35", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20221201/entities/gbq_results/article/article_718.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s11263-017-1021-y"
      }
    ]
     

    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/s11263-017-1021-y'

    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/s11263-017-1021-y'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11263-017-1021-y'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11263-017-1021-y'


     

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

    146 TRIPLES      21 PREDICATES      66 URIs      51 LITERALS      6 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s11263-017-1021-y schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nc750dc4361de4091a81d1aaf056ddd89
    4 schema:citation sg:pub.10.1007/11744023_17
    5 sg:pub.10.1007/11744085_44
    6 sg:pub.10.1007/978-3-319-10578-9_53
    7 sg:pub.10.1007/978-3-319-10593-2_21
    8 sg:pub.10.1007/978-3-642-15549-9_1
    9 sg:pub.10.1007/978-3-642-33718-5_29
    10 sg:pub.10.1023/a:1014573219977
    11 schema:datePublished 2017-06-03
    12 schema:datePublishedReg 2017-06-03
    13 schema:description Previous joint/guided filters directly transfer structural information from the reference to the target image. In this paper, we analyze the major drawback—that is, there may be completely different edges in the two images. Simply considering all patterns could introduce significant errors. To address this issue, we propose the concept of mutual-structure, which refers to the structural information that is contained in both images and thus can be safely enhanced by joint filtering. We also use an untraditional objective function that can be efficiently optimized to yield mutual structure. Our method results in important edge preserving property, which greatly benefits depth completion, optical flow estimation, image enhancement, stereo matching, to name a few.
    14 schema:genre article
    15 schema:isAccessibleForFree false
    16 schema:isPartOf N69d72ff357b742a4a02fc2cf8ea3dcef
    17 Ncbe8ec4e0ce04d0d8d0d1a602969d456
    18 sg:journal.1032807
    19 schema:keywords completion
    20 concept
    21 depth completion
    22 different edges
    23 drawbacks
    24 edge
    25 enhancement
    26 error
    27 estimation
    28 filter
    29 filtering
    30 flow estimation
    31 function
    32 image enhancement
    33 images
    34 important edges
    35 information
    36 issues
    37 joint filtering
    38 joint/
    39 major drawback
    40 matching
    41 method
    42 mutual structure
    43 objective function
    44 optical flow estimation
    45 paper
    46 patterns
    47 properties
    48 reference
    49 significant errors
    50 stereo matching
    51 structural information
    52 structure
    53 target image
    54 schema:name Mutual-Structure for Joint Filtering
    55 schema:pagination 19-33
    56 schema:productId N66b16097867041b8b96098ab4b92b593
    57 Ne5ccddff23ba4ea387f3d9c267a269e7
    58 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085762463
    59 https://doi.org/10.1007/s11263-017-1021-y
    60 schema:sdDatePublished 2022-12-01T06:35
    61 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    62 schema:sdPublisher N7d8fba2a170541fbbc22fc0dc2a2352f
    63 schema:url https://doi.org/10.1007/s11263-017-1021-y
    64 sgo:license sg:explorer/license/
    65 sgo:sdDataset articles
    66 rdf:type schema:ScholarlyArticle
    67 N66b16097867041b8b96098ab4b92b593 schema:name dimensions_id
    68 schema:value pub.1085762463
    69 rdf:type schema:PropertyValue
    70 N69d72ff357b742a4a02fc2cf8ea3dcef schema:issueNumber 1-3
    71 rdf:type schema:PublicationIssue
    72 N6da99daa4a6b4e29a69b278f43470279 rdf:first sg:person.011131772265.04
    73 rdf:rest N7fd32868d1f8488bafe334f426535ece
    74 N7d8fba2a170541fbbc22fc0dc2a2352f schema:name Springer Nature - SN SciGraph project
    75 rdf:type schema:Organization
    76 N7fd32868d1f8488bafe334f426535ece rdf:first sg:person.01005051540.26
    77 rdf:rest rdf:nil
    78 Nc750dc4361de4091a81d1aaf056ddd89 rdf:first sg:person.016165121117.35
    79 rdf:rest Nef4aca7bd97b4441a6d4b328dd63a3c0
    80 Ncbe8ec4e0ce04d0d8d0d1a602969d456 schema:volumeNumber 125
    81 rdf:type schema:PublicationVolume
    82 Ne5ccddff23ba4ea387f3d9c267a269e7 schema:name doi
    83 schema:value 10.1007/s11263-017-1021-y
    84 rdf:type schema:PropertyValue
    85 Nef4aca7bd97b4441a6d4b328dd63a3c0 rdf:first sg:person.012071567503.69
    86 rdf:rest N6da99daa4a6b4e29a69b278f43470279
    87 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    88 schema:name Information and Computing Sciences
    89 rdf:type schema:DefinedTerm
    90 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    91 schema:name Artificial Intelligence and Image Processing
    92 rdf:type schema:DefinedTerm
    93 sg:grant.7432685 http://pending.schema.org/fundedItem sg:pub.10.1007/s11263-017-1021-y
    94 rdf:type schema:MonetaryGrant
    95 sg:journal.1032807 schema:issn 0920-5691
    96 1573-1405
    97 schema:name International Journal of Computer Vision
    98 schema:publisher Springer Nature
    99 rdf:type schema:Periodical
    100 sg:person.01005051540.26 schema:affiliation grid-institutes:grid.10784.3a
    101 schema:familyName Jia
    102 schema:givenName Jiaya
    103 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01005051540.26
    104 rdf:type schema:Person
    105 sg:person.011131772265.04 schema:affiliation grid-institutes:None
    106 schema:familyName Xu
    107 schema:givenName Li
    108 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011131772265.04
    109 rdf:type schema:Person
    110 sg:person.012071567503.69 schema:affiliation grid-institutes:grid.10784.3a
    111 schema:familyName Zhou
    112 schema:givenName Chao
    113 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012071567503.69
    114 rdf:type schema:Person
    115 sg:person.016165121117.35 schema:affiliation grid-institutes:grid.10784.3a
    116 schema:familyName Shen
    117 schema:givenName Xiaoyong
    118 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016165121117.35
    119 rdf:type schema:Person
    120 sg:pub.10.1007/11744023_17 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013281471
    121 https://doi.org/10.1007/11744023_17
    122 rdf:type schema:CreativeWork
    123 sg:pub.10.1007/11744085_44 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009956269
    124 https://doi.org/10.1007/11744085_44
    125 rdf:type schema:CreativeWork
    126 sg:pub.10.1007/978-3-319-10578-9_53 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018943407
    127 https://doi.org/10.1007/978-3-319-10578-9_53
    128 rdf:type schema:CreativeWork
    129 sg:pub.10.1007/978-3-319-10593-2_21 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009765819
    130 https://doi.org/10.1007/978-3-319-10593-2_21
    131 rdf:type schema:CreativeWork
    132 sg:pub.10.1007/978-3-642-15549-9_1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039676932
    133 https://doi.org/10.1007/978-3-642-15549-9_1
    134 rdf:type schema:CreativeWork
    135 sg:pub.10.1007/978-3-642-33718-5_29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052949246
    136 https://doi.org/10.1007/978-3-642-33718-5_29
    137 rdf:type schema:CreativeWork
    138 sg:pub.10.1023/a:1014573219977 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004426816
    139 https://doi.org/10.1023/a:1014573219977
    140 rdf:type schema:CreativeWork
    141 grid-institutes:None schema:alternateName SenseTime Group Limited, Shatin, China
    142 schema:name SenseTime Group Limited, Shatin, China
    143 rdf:type schema:Organization
    144 grid-institutes:grid.10784.3a schema:alternateName The Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, NT, Hong Kong
    145 schema:name The Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, NT, Hong Kong
    146 rdf:type schema:Organization
     




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


    ...