Temporally Consistent Depth Estimation in Videos with Recurrent Architectures View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2019-01-23

AUTHORS

Denis Tananaev , Huizhong Zhou , Benjamin Ummenhofer , Thomas Brox

ABSTRACT

Convolutional networks trained on large RGB-D datasets have enabled depth estimation from a single image. Many works on automotive applications rely on such approaches. However, all existing methods work on a frame-by-frame manner when applied to videos, which leads to inconsistent depth estimates over time. In this paper, we introduce for the first time an approach that yields temporally consistent depth estimates over multiple frames of a video. This is done by a dedicated architecture based on convolutional LSTM units and layer normalization. Our approach achieves superior performance on several error metrics when compared to independent frame processing. This also shows in an improved quality of the reconstructed multi-view point clouds. More... »

PAGES

689-701

Book

TITLE

Computer Vision – ECCV 2018 Workshops

ISBN

978-3-030-11014-7
978-3-030-11015-4

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-030-11015-4_52

DOI

http://dx.doi.org/10.1007/978-3-030-11015-4_52

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1111703398


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": "Robert Bosch GmbH, Stuttgart, Germany", 
          "id": "http://www.grid.ac/institutes/grid.6584.f", 
          "name": [
            "University of Freiburg, Freiburg im Breisgau, Germany", 
            "Robert Bosch GmbH, Stuttgart, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Tananaev", 
        "givenName": "Denis", 
        "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": "Zhou", 
        "givenName": "Huizhong", 
        "id": "sg:person.015337214304.05", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015337214304.05"
        ], 
        "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": "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": "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": "2019-01-23", 
    "datePublishedReg": "2019-01-23", 
    "description": "Convolutional networks trained on large RGB-D datasets have enabled depth estimation from a single image. Many works on automotive applications rely on such approaches. However, all existing methods work on a frame-by-frame manner when applied to videos, which leads to inconsistent depth estimates over time. In this paper, we introduce for the first time an approach that yields temporally consistent depth estimates over multiple frames of a video. This is done by a dedicated architecture based on convolutional LSTM units and layer normalization. Our approach achieves superior performance on several error metrics when compared to independent frame processing. This also shows in an improved quality of the reconstructed multi-view point clouds.", 
    "editor": [
      {
        "familyName": "Leal-Taix\u00e9", 
        "givenName": "Laura", 
        "type": "Person"
      }, 
      {
        "familyName": "Roth", 
        "givenName": "Stefan", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-030-11015-4_52", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-030-11014-7", 
        "978-3-030-11015-4"
      ], 
      "name": "Computer Vision \u2013 ECCV 2018 Workshops", 
      "type": "Book"
    }, 
    "keywords": [
      "depth estimation", 
      "large RGB-D dataset", 
      "consistent depth estimation", 
      "RGB-D dataset", 
      "multi-view point clouds", 
      "convolutional network", 
      "dedicated architecture", 
      "layer normalization", 
      "recurrent architecture", 
      "LSTM units", 
      "single image", 
      "frame manner", 
      "frame processing", 
      "multiple frames", 
      "point clouds", 
      "error metrics", 
      "video", 
      "superior performance", 
      "automotive applications", 
      "architecture", 
      "such approaches", 
      "depth estimates", 
      "dataset", 
      "cloud", 
      "network", 
      "consistent depth", 
      "frame", 
      "metrics", 
      "images", 
      "estimation", 
      "processing", 
      "applications", 
      "performance", 
      "improved quality", 
      "time", 
      "quality", 
      "work", 
      "first time", 
      "depth", 
      "method", 
      "approach", 
      "normalization", 
      "manner", 
      "units", 
      "estimates", 
      "paper"
    ], 
    "name": "Temporally Consistent Depth Estimation in Videos with Recurrent Architectures", 
    "pagination": "689-701", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1111703398"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-030-11015-4_52"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-030-11015-4_52", 
      "https://app.dimensions.ai/details/publication/pub.1111703398"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-10-01T07:00", 
    "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_77.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-030-11015-4_52"
  }
]
 

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.10.1007/978-3-030-11015-4_52'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-11015-4_52'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-11015-4_52'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-11015-4_52'


 

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

134 TRIPLES      22 PREDICATES      70 URIs      63 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-030-11015-4_52 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N01ecb071d83c40c5ac102eb37037e4c0
4 schema:datePublished 2019-01-23
5 schema:datePublishedReg 2019-01-23
6 schema:description Convolutional networks trained on large RGB-D datasets have enabled depth estimation from a single image. Many works on automotive applications rely on such approaches. However, all existing methods work on a frame-by-frame manner when applied to videos, which leads to inconsistent depth estimates over time. In this paper, we introduce for the first time an approach that yields temporally consistent depth estimates over multiple frames of a video. This is done by a dedicated architecture based on convolutional LSTM units and layer normalization. Our approach achieves superior performance on several error metrics when compared to independent frame processing. This also shows in an improved quality of the reconstructed multi-view point clouds.
7 schema:editor N48bdb8b08e064dfab88d7222eda2e1a3
8 schema:genre chapter
9 schema:isAccessibleForFree false
10 schema:isPartOf N6a92a1a2daf6462fbcf9e1877eaa7160
11 schema:keywords LSTM units
12 RGB-D dataset
13 applications
14 approach
15 architecture
16 automotive applications
17 cloud
18 consistent depth
19 consistent depth estimation
20 convolutional network
21 dataset
22 dedicated architecture
23 depth
24 depth estimates
25 depth estimation
26 error metrics
27 estimates
28 estimation
29 first time
30 frame
31 frame manner
32 frame processing
33 images
34 improved quality
35 large RGB-D dataset
36 layer normalization
37 manner
38 method
39 metrics
40 multi-view point clouds
41 multiple frames
42 network
43 normalization
44 paper
45 performance
46 point clouds
47 processing
48 quality
49 recurrent architecture
50 single image
51 such approaches
52 superior performance
53 time
54 units
55 video
56 work
57 schema:name Temporally Consistent Depth Estimation in Videos with Recurrent Architectures
58 schema:pagination 689-701
59 schema:productId N051c099738804dd49fc834e00ee22268
60 Nf38bbea964644f32a86149d29729e4bb
61 schema:publisher N087e2203df294bb5b7d1352af2939498
62 schema:sameAs https://app.dimensions.ai/details/publication/pub.1111703398
63 https://doi.org/10.1007/978-3-030-11015-4_52
64 schema:sdDatePublished 2022-10-01T07:00
65 schema:sdLicense https://scigraph.springernature.com/explorer/license/
66 schema:sdPublisher N7329a5415a8b43849f70dd077301c116
67 schema:url https://doi.org/10.1007/978-3-030-11015-4_52
68 sgo:license sg:explorer/license/
69 sgo:sdDataset chapters
70 rdf:type schema:Chapter
71 N01ecb071d83c40c5ac102eb37037e4c0 rdf:first N0e9dabd061e643ca85a69e88b225cd81
72 rdf:rest Ne5ae53cbc3f5474a92365d389d1e5d7b
73 N051c099738804dd49fc834e00ee22268 schema:name doi
74 schema:value 10.1007/978-3-030-11015-4_52
75 rdf:type schema:PropertyValue
76 N087e2203df294bb5b7d1352af2939498 schema:name Springer Nature
77 rdf:type schema:Organisation
78 N0e9dabd061e643ca85a69e88b225cd81 schema:affiliation grid-institutes:grid.6584.f
79 schema:familyName Tananaev
80 schema:givenName Denis
81 rdf:type schema:Person
82 N0f844b7afde2406ca9529f117b2e42e5 schema:familyName Roth
83 schema:givenName Stefan
84 rdf:type schema:Person
85 N48bdb8b08e064dfab88d7222eda2e1a3 rdf:first Nf674bde597874b30a95f65498ec7c060
86 rdf:rest Neab6080f78a44d83aec64d486576920b
87 N56332da8a24549cabfd1fd5ef92d4eb7 rdf:first sg:person.012443225372.65
88 rdf:rest rdf:nil
89 N61216df0768f4d3b9c83b0957d1f7cb5 rdf:first sg:person.010435022672.00
90 rdf:rest N56332da8a24549cabfd1fd5ef92d4eb7
91 N6a92a1a2daf6462fbcf9e1877eaa7160 schema:isbn 978-3-030-11014-7
92 978-3-030-11015-4
93 schema:name Computer Vision – ECCV 2018 Workshops
94 rdf:type schema:Book
95 N7329a5415a8b43849f70dd077301c116 schema:name Springer Nature - SN SciGraph project
96 rdf:type schema:Organization
97 Ne5ae53cbc3f5474a92365d389d1e5d7b rdf:first sg:person.015337214304.05
98 rdf:rest N61216df0768f4d3b9c83b0957d1f7cb5
99 Neab6080f78a44d83aec64d486576920b rdf:first N0f844b7afde2406ca9529f117b2e42e5
100 rdf:rest rdf:nil
101 Nf38bbea964644f32a86149d29729e4bb schema:name dimensions_id
102 schema:value pub.1111703398
103 rdf:type schema:PropertyValue
104 Nf674bde597874b30a95f65498ec7c060 schema:familyName Leal-Taixé
105 schema:givenName Laura
106 rdf:type schema:Person
107 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
108 schema:name Information and Computing Sciences
109 rdf:type schema:DefinedTerm
110 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
111 schema:name Artificial Intelligence and Image Processing
112 rdf:type schema:DefinedTerm
113 sg:person.010435022672.00 schema:affiliation grid-institutes:grid.5963.9
114 schema:familyName Ummenhofer
115 schema:givenName Benjamin
116 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010435022672.00
117 rdf:type schema:Person
118 sg:person.012443225372.65 schema:affiliation grid-institutes:grid.5963.9
119 schema:familyName Brox
120 schema:givenName Thomas
121 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65
122 rdf:type schema:Person
123 sg:person.015337214304.05 schema:affiliation grid-institutes:grid.5963.9
124 schema:familyName Zhou
125 schema:givenName Huizhong
126 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015337214304.05
127 rdf:type schema:Person
128 grid-institutes:grid.5963.9 schema:alternateName University of Freiburg, Freiburg im Breisgau, Germany
129 schema:name University of Freiburg, Freiburg im Breisgau, Germany
130 rdf:type schema:Organization
131 grid-institutes:grid.6584.f schema:alternateName Robert Bosch GmbH, Stuttgart, Germany
132 schema:name Robert Bosch GmbH, Stuttgart, Germany
133 University of Freiburg, Freiburg im Breisgau, Germany
134 rdf:type schema:Organization
 




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


...