2018-10-07
AUTHORSRuoteng Li , Robby T. Tan , Loong-Fah Cheong
ABSTRACTOptical flow estimation in rainy scenes is challenging due to degradation caused by rain streaks and rain accumulation, where the latter refers to the poor visibility of remote scenes due to intense rainfall. To resolve the problem, we introduce a residue channel, a single channel (gray) image that is free from rain, and its colored version, a colored-residue image. We propose to utilize these two rain-free images in computing optical flow. To deal with the loss of contrast and the attendant sensitivity to noise, we decompose each of the input images into a piecewise-smooth structure layer and a high-frequency fine-detail texture layer. We combine the colored-residue images and structure layers in a unified objective function, so that the estimation of optical flow can be more robust. Results on both synthetic and real images show that our algorithm outperforms existing methods on different types of rain sequences. To our knowledge, this is the first optical flow method specifically dealing with rain. We also provide an optical flow dataset consisting of both synthetic and real rain images. More... »
PAGES299-317
Computer Vision – ECCV 2018
ISBN
978-3-030-01266-3
978-3-030-01267-0
http://scigraph.springernature.com/pub.10.1007/978-3-030-01267-0_18
DOIhttp://dx.doi.org/10.1007/978-3-030-01267-0_18
DIMENSIONShttps://app.dimensions.ai/details/publication/pub.1107463399
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/2008/0299",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Other Physical Sciences",
"type": "DefinedTerm"
},
{
"id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/02",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Physical Sciences",
"type": "DefinedTerm"
}
],
"author": [
{
"affiliation": {
"alternateName": "National University of Singapore",
"id": "https://www.grid.ac/institutes/grid.4280.e",
"name": [
"National University of Singapore, Singapore, Singapore"
],
"type": "Organization"
},
"familyName": "Li",
"givenName": "Ruoteng",
"type": "Person"
},
{
"affiliation": {
"alternateName": "Yale-NUS College",
"id": "https://www.grid.ac/institutes/grid.463064.3",
"name": [
"National University of Singapore, Singapore, Singapore",
"Yale-NUS College, Singapore, Singapore"
],
"type": "Organization"
},
"familyName": "Tan",
"givenName": "Robby T.",
"id": "sg:person.013234265355.33",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013234265355.33"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "National University of Singapore",
"id": "https://www.grid.ac/institutes/grid.4280.e",
"name": [
"National University of Singapore, Singapore, Singapore"
],
"type": "Organization"
},
"familyName": "Cheong",
"givenName": "Loong-Fah",
"id": "sg:person.012771501275.98",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012771501275.98"
],
"type": "Person"
}
],
"citation": [
{
"id": "sg:pub.10.1007/978-3-642-33783-3_44",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1004909083",
"https://doi.org/10.1007/978-3-642-33783-3_44"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/978-3-540-69321-5_40",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1010541599",
"https://doi.org/10.1007/978-3-540-69321-5_40"
],
"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.10.1007/11744023_17",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1013281471",
"https://doi.org/10.1007/11744023_17"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/978-3-642-03061-1_2",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1021250474",
"https://doi.org/10.1007/978-3-642-03061-1_2"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/bf01420984",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1021499342",
"https://doi.org/10.1007/bf01420984"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/bf01420984",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1021499342",
"https://doi.org/10.1007/bf01420984"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/2024156.2024208",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1023950565"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/978-3-540-74936-3_16",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1028192541",
"https://doi.org/10.1007/978-3-540-74936-3_16"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/978-3-540-74936-3_16",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1028192541",
"https://doi.org/10.1007/978-3-540-74936-3_16"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1023/b:visi.0000045324.43199.43",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1028948709",
"https://doi.org/10.1023/b:visi.0000045324.43199.43"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s11263-010-0390-2",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1034215603",
"https://doi.org/10.1007/s11263-010-0390-2"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1006/cviu.1996.0006",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1036996571"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s11263-006-0028-6",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1039020216",
"https://doi.org/10.1007/s11263-006-0028-6"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1016/0004-3702(81)90024-2",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1039049535"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s11263-016-0908-3",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1050786271",
"https://doi.org/10.1007/s11263-016-0908-3"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tcsvt.2014.2308628",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061576283"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tpami.2010.143",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061743864"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tpami.2010.147",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061743868"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/1141911.1141985",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1063151990"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1364/josaa.31.001049",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1065164466"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1561/0600000009",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1068000461"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/smbv.2001.988771",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093174803"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2014.435",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093389075"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2016.438",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093422401"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/iccv.2015.316",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093818236"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/iccv.2015.388",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093865933"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2008.4587845",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093874696"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/iccv.2015.456",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1094324600"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/iccv.2013.175",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1094480864"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2000.855826",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1094696632"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2016.157",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1095160299"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2015.7298720",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1095396135"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2015.7298925",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1095719726"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2017.179",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1095843462"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2017.615",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1095851603"
],
"type": "CreativeWork"
}
],
"datePublished": "2018-10-07",
"datePublishedReg": "2018-10-07",
"description": "Optical flow estimation in rainy scenes is challenging due to degradation caused by rain streaks and rain accumulation, where the latter refers to the poor visibility of remote scenes due to intense rainfall. To resolve the problem, we introduce a residue channel, a single channel (gray) image that is free from rain, and its colored version, a colored-residue image. We propose to utilize these two rain-free images in computing optical flow. To deal with the loss of contrast and the attendant sensitivity to noise, we decompose each of the input images into a piecewise-smooth structure layer and a high-frequency fine-detail texture layer. We combine the colored-residue images and structure layers in a unified objective function, so that the estimation of optical flow can be more robust. Results on both synthetic and real images show that our algorithm outperforms existing methods on different types of rain sequences. To our knowledge, this is the first optical flow method specifically dealing with rain. We also provide an optical flow dataset consisting of both synthetic and real rain images.",
"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.10.1007/978-3-030-01267-0_18",
"inLanguage": [
"en"
],
"isAccessibleForFree": false,
"isPartOf": {
"isbn": [
"978-3-030-01266-3",
"978-3-030-01267-0"
],
"name": "Computer Vision \u2013 ECCV 2018",
"type": "Book"
},
"name": "Robust Optical Flow in Rainy Scenes",
"pagination": "299-317",
"productId": [
{
"name": "doi",
"type": "PropertyValue",
"value": [
"10.1007/978-3-030-01267-0_18"
]
},
{
"name": "readcube_id",
"type": "PropertyValue",
"value": [
"f07b4c517324a8de06ff27473a38fcd9dcaa160ed028f11794e5910a1ff09da3"
]
},
{
"name": "dimensions_id",
"type": "PropertyValue",
"value": [
"pub.1107463399"
]
}
],
"publisher": {
"location": "Cham",
"name": "Springer International Publishing",
"type": "Organisation"
},
"sameAs": [
"https://doi.org/10.1007/978-3-030-01267-0_18",
"https://app.dimensions.ai/details/publication/pub.1107463399"
],
"sdDataset": "chapters",
"sdDatePublished": "2019-04-16T04:39",
"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/v90/0000000321_0000000321/records_74910_00000000.jsonl",
"type": "Chapter",
"url": "https://link.springer.com/10.1007%2F978-3-030-01267-0_18"
}
]Download the RDF metadata as: json-ld nt turtle xml License info
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.10.1007/978-3-030-01267-0_18'
N-Triples is a line-based linked data format ideal for batch operations.
curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01267-0_18'
Turtle is a human-readable linked data format.
curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01267-0_18'
RDF/XML is a standard XML format for linked data.
curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01267-0_18'
This table displays all metadata directly associated to this object as RDF triples.
206 TRIPLES
23 PREDICATES
59 URIs
19 LITERALS
8 BLANK NODES