Global, Dense Multiscale Reconstruction for a Billion Points View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2017-06-03

AUTHORS

Benjamin Ummenhofer, Thomas Brox

ABSTRACT

We present a variational approach for surface reconstruction from a set of oriented points with scale information. We focus particularly on scenarios with nonuniform point densities due to images taken from different distances. In contrast to previous methods, we integrate the scale information in the objective and globally optimize the signed distance function of the surface on a balanced octree grid. We use a finite element discretization on the dual structure of the octree minimizing the number of variables. The tetrahedral mesh is generated efficiently with a lookup table which allows to map octree cells to the nodes of the finite elements. We optimize memory efficiency by data aggregation, such that robust data terms can be used even on very large scenes. The surface normals are explicitly optimized and used for surface extraction to improve the reconstruction at edges and corners. More... »

PAGES

82-94

References to SciGraph publications

  • 2014. Robust Global Translations with 1DSfM in COMPUTER VISION – ECCV 2014
  • 1992-03-01. On the difficulty of triangulating three-dimensional Nonconvex Polyhedra in DISCRETE & COMPUTATIONAL GEOMETRY
  • 2010. Building Rome on a Cloudless Day in COMPUTER VISION – ECCV 2010
  • 2015-04-28. Robust Poisson Surface Reconstruction in SCALE SPACE AND VARIATIONAL METHODS IN COMPUTER VISION
  • 2012. Scale Robust Multi View Stereo in COMPUTER VISION – ECCV 2012
  • 1993-06. Seams and wedges in plastering: A 3-D hexahedral mesh generation algorithm in ENGINEERING WITH COMPUTERS
  • 2009. Advances in Octree-Based All-Hexahedral Mesh Generation: Handling Sharp Features in PROCEEDINGS OF THE 18TH INTERNATIONAL MESHING ROUNDTABLE
  • 2011. TGV-Fusion in RAINBOW OF COMPUTER SCIENCE
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s11263-017-1017-7

    DOI

    http://dx.doi.org/10.1007/s11263-017-1017-7

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1085752264


    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/2008/0806", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information Systems", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Department of Computer Science, University of Freiburg, 79110, Freiburg, Germany", 
              "id": "http://www.grid.ac/institutes/grid.5963.9", 
              "name": [
                "Department of Computer Science, University of Freiburg, 79110, Freiburg, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Ummenhofer", 
            "givenName": "Benjamin", 
            "id": "sg:person.010435022672.00", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010435022672.00"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Computer Science, University of Freiburg, 79110, Freiburg, Germany", 
              "id": "http://www.grid.ac/institutes/grid.5963.9", 
              "name": [
                "Department of Computer Science, University of Freiburg, 79110, Freiburg, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Brox", 
            "givenName": "Thomas", 
            "id": "sg:person.012443225372.65", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/bf01199047", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046365667", 
              "https://doi.org/10.1007/bf01199047"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-33712-3_29", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1029878459", 
              "https://doi.org/10.1007/978-3-642-33712-3_29"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-04319-2_5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1025953478", 
              "https://doi.org/10.1007/978-3-642-04319-2_5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-19391-0_18", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1023719332", 
              "https://doi.org/10.1007/978-3-642-19391-0_18"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf02187840", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1053651976", 
              "https://doi.org/10.1007/bf02187840"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-18461-6_42", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1023604055", 
              "https://doi.org/10.1007/978-3-319-18461-6_42"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-15561-1_27", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1020939024", 
              "https://doi.org/10.1007/978-3-642-15561-1_27"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-10578-9_5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001226326", 
              "https://doi.org/10.1007/978-3-319-10578-9_5"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2017-06-03", 
        "datePublishedReg": "2017-06-03", 
        "description": "We present a variational approach for surface reconstruction from a set of oriented points with scale information. We focus particularly on scenarios with nonuniform point densities due to images taken from different distances. In contrast to previous methods, we integrate the scale information in the objective and globally optimize the signed distance function of the surface on a balanced octree grid. We use a finite element discretization on the dual structure of the octree minimizing the number of variables. The tetrahedral mesh is generated efficiently with a lookup table which allows to map octree cells to the nodes of the finite elements. We optimize memory efficiency by data aggregation, such that robust data terms can be used even on very large scenes. The surface normals are explicitly optimized and used for surface extraction to improve the reconstruction at edges and corners.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s11263-017-1017-7", 
        "isAccessibleForFree": true, 
        "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": [
          "scale information", 
          "robust data term", 
          "data aggregation", 
          "large scenes", 
          "finite element discretization", 
          "memory efficiency", 
          "finite elements", 
          "data term", 
          "surface extraction", 
          "multiscale reconstruction", 
          "surface normals", 
          "element discretization", 
          "previous methods", 
          "octree grids", 
          "lookup table", 
          "tetrahedral meshes", 
          "distance function", 
          "surface reconstruction", 
          "point density", 
          "number of variables", 
          "octree cells", 
          "information", 
          "different distances", 
          "octree", 
          "scene", 
          "grid", 
          "nodes", 
          "images", 
          "variational approach", 
          "reconstruction", 
          "scenarios", 
          "surface", 
          "mesh", 
          "discretization", 
          "efficiency", 
          "set", 
          "density", 
          "corner", 
          "extraction", 
          "dual structure", 
          "table", 
          "point", 
          "edge", 
          "structure", 
          "method", 
          "elements", 
          "distance", 
          "terms", 
          "approach", 
          "number", 
          "objective", 
          "aggregation", 
          "function", 
          "variables", 
          "contrast", 
          "cells", 
          "normals"
        ], 
        "name": "Global, Dense Multiscale Reconstruction for a Billion Points", 
        "pagination": "82-94", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1085752264"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s11263-017-1017-7"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s11263-017-1017-7", 
          "https://app.dimensions.ai/details/publication/pub.1085752264"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-10-01T06:43", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20221001/entities/gbq_results/article/article_743.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s11263-017-1017-7"
      }
    ]
     

    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/s11263-017-1017-7'

    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/s11263-017-1017-7'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11263-017-1017-7'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11263-017-1017-7'


     

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

    153 TRIPLES      21 PREDICATES      89 URIs      73 LITERALS      6 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s11263-017-1017-7 schema:about anzsrc-for:08
    2 anzsrc-for:0806
    3 schema:author Nb4f8c07189c941d5bd5f17a2c067be52
    4 schema:citation sg:pub.10.1007/978-3-319-10578-9_5
    5 sg:pub.10.1007/978-3-319-18461-6_42
    6 sg:pub.10.1007/978-3-642-04319-2_5
    7 sg:pub.10.1007/978-3-642-15561-1_27
    8 sg:pub.10.1007/978-3-642-19391-0_18
    9 sg:pub.10.1007/978-3-642-33712-3_29
    10 sg:pub.10.1007/bf01199047
    11 sg:pub.10.1007/bf02187840
    12 schema:datePublished 2017-06-03
    13 schema:datePublishedReg 2017-06-03
    14 schema:description We present a variational approach for surface reconstruction from a set of oriented points with scale information. We focus particularly on scenarios with nonuniform point densities due to images taken from different distances. In contrast to previous methods, we integrate the scale information in the objective and globally optimize the signed distance function of the surface on a balanced octree grid. We use a finite element discretization on the dual structure of the octree minimizing the number of variables. The tetrahedral mesh is generated efficiently with a lookup table which allows to map octree cells to the nodes of the finite elements. We optimize memory efficiency by data aggregation, such that robust data terms can be used even on very large scenes. The surface normals are explicitly optimized and used for surface extraction to improve the reconstruction at edges and corners.
    15 schema:genre article
    16 schema:isAccessibleForFree true
    17 schema:isPartOf Nd321aae51d19493787e71fc478f97936
    18 Nf36fd281d7ea4204a47fa2ebcda91e07
    19 sg:journal.1032807
    20 schema:keywords aggregation
    21 approach
    22 cells
    23 contrast
    24 corner
    25 data aggregation
    26 data term
    27 density
    28 different distances
    29 discretization
    30 distance
    31 distance function
    32 dual structure
    33 edge
    34 efficiency
    35 element discretization
    36 elements
    37 extraction
    38 finite element discretization
    39 finite elements
    40 function
    41 grid
    42 images
    43 information
    44 large scenes
    45 lookup table
    46 memory efficiency
    47 mesh
    48 method
    49 multiscale reconstruction
    50 nodes
    51 normals
    52 number
    53 number of variables
    54 objective
    55 octree
    56 octree cells
    57 octree grids
    58 point
    59 point density
    60 previous methods
    61 reconstruction
    62 robust data term
    63 scale information
    64 scenarios
    65 scene
    66 set
    67 structure
    68 surface
    69 surface extraction
    70 surface normals
    71 surface reconstruction
    72 table
    73 terms
    74 tetrahedral meshes
    75 variables
    76 variational approach
    77 schema:name Global, Dense Multiscale Reconstruction for a Billion Points
    78 schema:pagination 82-94
    79 schema:productId N38f80c83aae548eb93324c162672f3ca
    80 N51bd1285019f4707821d6fb1c9b86490
    81 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085752264
    82 https://doi.org/10.1007/s11263-017-1017-7
    83 schema:sdDatePublished 2022-10-01T06:43
    84 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    85 schema:sdPublisher N84e13e629c4346b68177837f0586c30b
    86 schema:url https://doi.org/10.1007/s11263-017-1017-7
    87 sgo:license sg:explorer/license/
    88 sgo:sdDataset articles
    89 rdf:type schema:ScholarlyArticle
    90 N14dc20710e074f83acc21f21d1d1a920 rdf:first sg:person.012443225372.65
    91 rdf:rest rdf:nil
    92 N38f80c83aae548eb93324c162672f3ca schema:name dimensions_id
    93 schema:value pub.1085752264
    94 rdf:type schema:PropertyValue
    95 N51bd1285019f4707821d6fb1c9b86490 schema:name doi
    96 schema:value 10.1007/s11263-017-1017-7
    97 rdf:type schema:PropertyValue
    98 N84e13e629c4346b68177837f0586c30b schema:name Springer Nature - SN SciGraph project
    99 rdf:type schema:Organization
    100 Nb4f8c07189c941d5bd5f17a2c067be52 rdf:first sg:person.010435022672.00
    101 rdf:rest N14dc20710e074f83acc21f21d1d1a920
    102 Nd321aae51d19493787e71fc478f97936 schema:volumeNumber 125
    103 rdf:type schema:PublicationVolume
    104 Nf36fd281d7ea4204a47fa2ebcda91e07 schema:issueNumber 1-3
    105 rdf:type schema:PublicationIssue
    106 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    107 schema:name Information and Computing Sciences
    108 rdf:type schema:DefinedTerm
    109 anzsrc-for:0806 schema:inDefinedTermSet anzsrc-for:
    110 schema:name Information Systems
    111 rdf:type schema:DefinedTerm
    112 sg:journal.1032807 schema:issn 0920-5691
    113 1573-1405
    114 schema:name International Journal of Computer Vision
    115 schema:publisher Springer Nature
    116 rdf:type schema:Periodical
    117 sg:person.010435022672.00 schema:affiliation grid-institutes:grid.5963.9
    118 schema:familyName Ummenhofer
    119 schema:givenName Benjamin
    120 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010435022672.00
    121 rdf:type schema:Person
    122 sg:person.012443225372.65 schema:affiliation grid-institutes:grid.5963.9
    123 schema:familyName Brox
    124 schema:givenName Thomas
    125 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65
    126 rdf:type schema:Person
    127 sg:pub.10.1007/978-3-319-10578-9_5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001226326
    128 https://doi.org/10.1007/978-3-319-10578-9_5
    129 rdf:type schema:CreativeWork
    130 sg:pub.10.1007/978-3-319-18461-6_42 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023604055
    131 https://doi.org/10.1007/978-3-319-18461-6_42
    132 rdf:type schema:CreativeWork
    133 sg:pub.10.1007/978-3-642-04319-2_5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025953478
    134 https://doi.org/10.1007/978-3-642-04319-2_5
    135 rdf:type schema:CreativeWork
    136 sg:pub.10.1007/978-3-642-15561-1_27 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020939024
    137 https://doi.org/10.1007/978-3-642-15561-1_27
    138 rdf:type schema:CreativeWork
    139 sg:pub.10.1007/978-3-642-19391-0_18 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023719332
    140 https://doi.org/10.1007/978-3-642-19391-0_18
    141 rdf:type schema:CreativeWork
    142 sg:pub.10.1007/978-3-642-33712-3_29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029878459
    143 https://doi.org/10.1007/978-3-642-33712-3_29
    144 rdf:type schema:CreativeWork
    145 sg:pub.10.1007/bf01199047 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046365667
    146 https://doi.org/10.1007/bf01199047
    147 rdf:type schema:CreativeWork
    148 sg:pub.10.1007/bf02187840 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053651976
    149 https://doi.org/10.1007/bf02187840
    150 rdf:type schema:CreativeWork
    151 grid-institutes:grid.5963.9 schema:alternateName Department of Computer Science, University of Freiburg, 79110, Freiburg, Germany
    152 schema:name Department of Computer Science, University of Freiburg, 79110, Freiburg, Germany
    153 rdf:type schema:Organization
     




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


    ...