Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2018-10-06

AUTHORS

Eddy Ilg , Tonmoy Saikia , Margret Keuper , Thomas Brox

ABSTRACT

Occlusions play an important role in disparity and optical flow estimation, since matching costs are not available in occluded areas and occlusions indicate depth or motion boundaries. Moreover, occlusions are relevant for motion segmentation and scene flow estimation. In this paper, we present an efficient learning-based approach to estimate occlusion areas jointly with disparities or optical flow. The estimated occlusions and motion boundaries clearly improve over the state-of-the-art. Moreover, we present networks with state-of-the-art performance on the popular KITTI benchmark and good generic performance. Making use of the estimated occlusions, we also show improved results on motion segmentation and scene flow estimation. More... »

PAGES

626-643

Book

TITLE

Computer Vision – ECCV 2018

ISBN

978-3-030-01257-1
978-3-030-01258-8

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-030-01258-8_38

DOI

http://dx.doi.org/10.1007/978-3-030-01258-8_38

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1107454799


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": "University of Freiburg, Freiburg im Breisgau, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "University of Freiburg, Freiburg im Breisgau, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ilg", 
        "givenName": "Eddy", 
        "id": "sg:person.014016531047.11", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014016531047.11"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Freiburg, Freiburg im Breisgau, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "University of Freiburg, Freiburg im Breisgau, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Saikia", 
        "givenName": "Tonmoy", 
        "id": "sg:person.016241126503.02", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016241126503.02"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Freiburg, Freiburg im Breisgau, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "University of Freiburg, Freiburg im Breisgau, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Keuper", 
        "givenName": "Margret", 
        "id": "sg:person.013477515133.33", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013477515133.33"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Freiburg, Freiburg im Breisgau, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "University of Freiburg, Freiburg im Breisgau, 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"
      }
    ], 
    "datePublished": "2018-10-06", 
    "datePublishedReg": "2018-10-06", 
    "description": "Occlusions play an important role in disparity and optical flow estimation, since matching costs are not available in occluded areas and occlusions indicate depth or motion boundaries. Moreover, occlusions are relevant for motion segmentation and scene flow estimation. In this paper, we present an efficient learning-based approach to estimate occlusion areas jointly with disparities or optical flow. The estimated occlusions and motion boundaries clearly improve over the state-of-the-art. Moreover, we present networks with state-of-the-art performance on the popular KITTI benchmark and good generic performance. Making use of the estimated occlusions, we also show improved results on motion segmentation and scene flow estimation.", 
    "editor": [
      {
        "familyName": "Ferrari", 
        "givenName": "Vittorio", 
        "type": "Person"
      }, 
      {
        "familyName": "Hebert", 
        "givenName": "Martial", 
        "type": "Person"
      }, 
      {
        "familyName": "Sminchisescu", 
        "givenName": "Cristian", 
        "type": "Person"
      }, 
      {
        "familyName": "Weiss", 
        "givenName": "Yair", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-030-01258-8_38", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-030-01257-1", 
        "978-3-030-01258-8"
      ], 
      "name": "Computer Vision \u2013 ECCV 2018", 
      "type": "Book"
    }, 
    "keywords": [
      "flow estimation", 
      "motion boundaries", 
      "scene flow estimation", 
      "motion segmentation", 
      "optical flow estimation", 
      "optical flow", 
      "generic network", 
      "popular KITTI benchmark", 
      "estimation", 
      "boundaries", 
      "improved results", 
      "flow", 
      "depth boundaries", 
      "motion", 
      "network", 
      "KITTI benchmark", 
      "occlusion areas", 
      "state", 
      "art performance", 
      "learning-based approach", 
      "performance", 
      "benchmarks", 
      "segmentation", 
      "approach", 
      "results", 
      "cost", 
      "important role", 
      "generic performance", 
      "art", 
      "area", 
      "depth", 
      "use", 
      "role", 
      "occlusion", 
      "paper", 
      "disparities"
    ], 
    "name": "Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation", 
    "pagination": "626-643", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1107454799"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-030-01258-8_38"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-030-01258-8_38", 
      "https://app.dimensions.ai/details/publication/pub.1107454799"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-10-01T06:56", 
    "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/chapter/chapter_325.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-030-01258-8_38"
  }
]
 

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.10.1007/978-3-030-01258-8_38'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01258-8_38'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01258-8_38'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01258-8_38'


 

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

131 TRIPLES      22 PREDICATES      60 URIs      53 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-030-01258-8_38 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N3eddea6726a04e66acca496352984ec4
4 schema:datePublished 2018-10-06
5 schema:datePublishedReg 2018-10-06
6 schema:description Occlusions play an important role in disparity and optical flow estimation, since matching costs are not available in occluded areas and occlusions indicate depth or motion boundaries. Moreover, occlusions are relevant for motion segmentation and scene flow estimation. In this paper, we present an efficient learning-based approach to estimate occlusion areas jointly with disparities or optical flow. The estimated occlusions and motion boundaries clearly improve over the state-of-the-art. Moreover, we present networks with state-of-the-art performance on the popular KITTI benchmark and good generic performance. Making use of the estimated occlusions, we also show improved results on motion segmentation and scene flow estimation.
7 schema:editor N67a88911a04c4fa683c20b15058e36ea
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf N29a7d52ba93f4b72b0d752c6289d1c38
11 schema:keywords KITTI benchmark
12 approach
13 area
14 art
15 art performance
16 benchmarks
17 boundaries
18 cost
19 depth
20 depth boundaries
21 disparities
22 estimation
23 flow
24 flow estimation
25 generic network
26 generic performance
27 important role
28 improved results
29 learning-based approach
30 motion
31 motion boundaries
32 motion segmentation
33 network
34 occlusion
35 occlusion areas
36 optical flow
37 optical flow estimation
38 paper
39 performance
40 popular KITTI benchmark
41 results
42 role
43 scene flow estimation
44 segmentation
45 state
46 use
47 schema:name Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation
48 schema:pagination 626-643
49 schema:productId N2e2b65871ee24e1483330d247d3c0724
50 N834e5adcd5ac4096b2469c9cd7434594
51 schema:publisher N1a33be159be84d4295c17bae80edb0b1
52 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107454799
53 https://doi.org/10.1007/978-3-030-01258-8_38
54 schema:sdDatePublished 2022-10-01T06:56
55 schema:sdLicense https://scigraph.springernature.com/explorer/license/
56 schema:sdPublisher Ne6da5ddb100f4cfc8ebab6818ca24d99
57 schema:url https://doi.org/10.1007/978-3-030-01258-8_38
58 sgo:license sg:explorer/license/
59 sgo:sdDataset chapters
60 rdf:type schema:Chapter
61 N1a33be159be84d4295c17bae80edb0b1 schema:name Springer Nature
62 rdf:type schema:Organisation
63 N1a96bcde14d24cee96a021f446fd7a9f rdf:first N2a19bf9a3e5f46f8a30c249d9e2ef890
64 rdf:rest rdf:nil
65 N1d612ed320b64991b630373d8e8902c3 rdf:first N609235ad9d374010a4af71f5172a867c
66 rdf:rest N4c026aa2683447e0a03296f1aaca076b
67 N29a7d52ba93f4b72b0d752c6289d1c38 schema:isbn 978-3-030-01257-1
68 978-3-030-01258-8
69 schema:name Computer Vision – ECCV 2018
70 rdf:type schema:Book
71 N2a19bf9a3e5f46f8a30c249d9e2ef890 schema:familyName Weiss
72 schema:givenName Yair
73 rdf:type schema:Person
74 N2e2b65871ee24e1483330d247d3c0724 schema:name dimensions_id
75 schema:value pub.1107454799
76 rdf:type schema:PropertyValue
77 N3eddea6726a04e66acca496352984ec4 rdf:first sg:person.014016531047.11
78 rdf:rest Nb355899d8ec44c74b8ab2c46e06b7e52
79 N4b05a9255f414c72808076a947dac0fa rdf:first sg:person.012443225372.65
80 rdf:rest rdf:nil
81 N4c026aa2683447e0a03296f1aaca076b rdf:first N79443a58321b466ebde22d31b176a1ca
82 rdf:rest N1a96bcde14d24cee96a021f446fd7a9f
83 N609235ad9d374010a4af71f5172a867c schema:familyName Hebert
84 schema:givenName Martial
85 rdf:type schema:Person
86 N67a88911a04c4fa683c20b15058e36ea rdf:first Na7a4a9b7e9f5464b804522dd9e2af547
87 rdf:rest N1d612ed320b64991b630373d8e8902c3
88 N79443a58321b466ebde22d31b176a1ca schema:familyName Sminchisescu
89 schema:givenName Cristian
90 rdf:type schema:Person
91 N834e5adcd5ac4096b2469c9cd7434594 schema:name doi
92 schema:value 10.1007/978-3-030-01258-8_38
93 rdf:type schema:PropertyValue
94 Na7a4a9b7e9f5464b804522dd9e2af547 schema:familyName Ferrari
95 schema:givenName Vittorio
96 rdf:type schema:Person
97 Nb355899d8ec44c74b8ab2c46e06b7e52 rdf:first sg:person.016241126503.02
98 rdf:rest Nec7fa5f70a8d493eb769ccdea4934562
99 Ne6da5ddb100f4cfc8ebab6818ca24d99 schema:name Springer Nature - SN SciGraph project
100 rdf:type schema:Organization
101 Nec7fa5f70a8d493eb769ccdea4934562 rdf:first sg:person.013477515133.33
102 rdf:rest N4b05a9255f414c72808076a947dac0fa
103 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
104 schema:name Information and Computing Sciences
105 rdf:type schema:DefinedTerm
106 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
107 schema:name Artificial Intelligence and Image Processing
108 rdf:type schema:DefinedTerm
109 sg:person.012443225372.65 schema:affiliation grid-institutes:grid.5963.9
110 schema:familyName Brox
111 schema:givenName Thomas
112 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65
113 rdf:type schema:Person
114 sg:person.013477515133.33 schema:affiliation grid-institutes:grid.5963.9
115 schema:familyName Keuper
116 schema:givenName Margret
117 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013477515133.33
118 rdf:type schema:Person
119 sg:person.014016531047.11 schema:affiliation grid-institutes:grid.5963.9
120 schema:familyName Ilg
121 schema:givenName Eddy
122 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014016531047.11
123 rdf:type schema:Person
124 sg:person.016241126503.02 schema:affiliation grid-institutes:grid.5963.9
125 schema:familyName Saikia
126 schema:givenName Tonmoy
127 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016241126503.02
128 rdf:type schema:Person
129 grid-institutes:grid.5963.9 schema:alternateName University of Freiburg, Freiburg im Breisgau, Germany
130 schema:name University of Freiburg, Freiburg im Breisgau, Germany
131 rdf:type schema:Organization
 




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


...