Loading…
A 3D Convolutional Neural Network for Light Field Depth Estimation
Depth estimation has always been a great challenge in the field of computer vision and machine learning. There is a rich literature focusing on depth estimation in stereo vision or in monocular imaging, while the domain of depth estimation in light field images is still in its infancy. The paper pro...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Citations: | Items that cite this one |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | cdi_FETCH-LOGICAL-c256t-d5fbdd28f2125a096c8342d4981979da895aad74fc5164f47db7a06098ff826f3 |
|---|---|
| cites | |
| container_end_page | 5 |
| container_issue | |
| container_start_page | 1 |
| container_title | |
| container_volume | |
| creator | Faluvegi, Agota Bolsee, Quentin Nedevschi, Sergiu Dadarlat, Vasile-Teodor Munteanu, Adrian |
| description | Depth estimation has always been a great challenge in the field of computer vision and machine learning. There is a rich literature focusing on depth estimation in stereo vision or in monocular imaging, while the domain of depth estimation in light field images is still in its infancy. The paper proposes a fully convolutional 3D neural network that estimates the disparity in light field images. The proposed method is parametric as it is able to adapt to input images of arbitrary size and it is lightweight and less prone to overfitting thanks to its fully convolutional nature. The experiments reveal competitive results against the state of the art, demonstrating the potential offered by deep learning solutions for disparity estimation in light field images. |
| doi_str_mv | 10.1109/IC3D48390.2019.8975996 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_8975996</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8975996</ieee_id><sourcerecordid>8975996</sourcerecordid><originalsourceid>FETCH-LOGICAL-c256t-d5fbdd28f2125a096c8342d4981979da895aad74fc5164f47db7a06098ff826f3</originalsourceid><addsrcrecordid>eNotj8tOwzAURA0SElXJFyAh_0CC3753WZIWKkV0U9aVG9s0EJoqcUH8PQW6OpuZMxpC7jgrOGd4vyxlpUAiKwTjWABajWguSIYWuBXANQcUl2QipMWcW2DXJBvHN8ZOcc3Aqgl5mFFZ0bLff_bdMbX93nX0ORyHP6SvfninsR9o3b7uEl20ofO0Coe0o_MxtR_ut3FDrqLrxpCdOSUvi_m6fMrr1eOynNV5I7RJuddx672AKLjQjqFpQCrhFQJHi94Baue8VbHR3KiorN9axwxDiBGEiXJKbv-9bQhhcxhO88P35vxa_gCaNEru</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A 3D Convolutional Neural Network for Light Field Depth Estimation</title><source>IEEE Xplore All Conference Series</source><creator>Faluvegi, Agota ; Bolsee, Quentin ; Nedevschi, Sergiu ; Dadarlat, Vasile-Teodor ; Munteanu, Adrian</creator><creatorcontrib>Faluvegi, Agota ; Bolsee, Quentin ; Nedevschi, Sergiu ; Dadarlat, Vasile-Teodor ; Munteanu, Adrian</creatorcontrib><description>Depth estimation has always been a great challenge in the field of computer vision and machine learning. There is a rich literature focusing on depth estimation in stereo vision or in monocular imaging, while the domain of depth estimation in light field images is still in its infancy. The paper proposes a fully convolutional 3D neural network that estimates the disparity in light field images. The proposed method is parametric as it is able to adapt to input images of arbitrary size and it is lightweight and less prone to overfitting thanks to its fully convolutional nature. The experiments reveal competitive results against the state of the art, demonstrating the potential offered by deep learning solutions for disparity estimation in light field images.</description><identifier>EISSN: 2379-1780</identifier><identifier>EISBN: 9781728151892</identifier><identifier>EISBN: 1728151899</identifier><identifier>DOI: 10.1109/IC3D48390.2019.8975996</identifier><language>eng</language><publisher>IEEE</publisher><subject>3D convolution ; CNN ; Computer vision ; Convolution ; Deep learning ; depth estimation ; disparity map ; EPI ; Estimation ; Focusing ; Light field image ; Neural networks ; Three-dimensional displays</subject><ispartof>2019 International Conference on 3D Immersion (IC3D), 2019, p.1-5</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c256t-d5fbdd28f2125a096c8342d4981979da895aad74fc5164f47db7a06098ff826f3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8975996$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8975996$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Faluvegi, Agota</creatorcontrib><creatorcontrib>Bolsee, Quentin</creatorcontrib><creatorcontrib>Nedevschi, Sergiu</creatorcontrib><creatorcontrib>Dadarlat, Vasile-Teodor</creatorcontrib><creatorcontrib>Munteanu, Adrian</creatorcontrib><title>A 3D Convolutional Neural Network for Light Field Depth Estimation</title><title>2019 International Conference on 3D Immersion (IC3D)</title><addtitle>IC3D</addtitle><description>Depth estimation has always been a great challenge in the field of computer vision and machine learning. There is a rich literature focusing on depth estimation in stereo vision or in monocular imaging, while the domain of depth estimation in light field images is still in its infancy. The paper proposes a fully convolutional 3D neural network that estimates the disparity in light field images. The proposed method is parametric as it is able to adapt to input images of arbitrary size and it is lightweight and less prone to overfitting thanks to its fully convolutional nature. The experiments reveal competitive results against the state of the art, demonstrating the potential offered by deep learning solutions for disparity estimation in light field images.</description><subject>3D convolution</subject><subject>CNN</subject><subject>Computer vision</subject><subject>Convolution</subject><subject>Deep learning</subject><subject>depth estimation</subject><subject>disparity map</subject><subject>EPI</subject><subject>Estimation</subject><subject>Focusing</subject><subject>Light field image</subject><subject>Neural networks</subject><subject>Three-dimensional displays</subject><issn>2379-1780</issn><isbn>9781728151892</isbn><isbn>1728151899</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2019</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj8tOwzAURA0SElXJFyAh_0CC3753WZIWKkV0U9aVG9s0EJoqcUH8PQW6OpuZMxpC7jgrOGd4vyxlpUAiKwTjWABajWguSIYWuBXANQcUl2QipMWcW2DXJBvHN8ZOcc3Aqgl5mFFZ0bLff_bdMbX93nX0ORyHP6SvfninsR9o3b7uEl20ofO0Coe0o_MxtR_ut3FDrqLrxpCdOSUvi_m6fMrr1eOynNV5I7RJuddx672AKLjQjqFpQCrhFQJHi94Baue8VbHR3KiorN9axwxDiBGEiXJKbv-9bQhhcxhO88P35vxa_gCaNEru</recordid><startdate>201912</startdate><enddate>201912</enddate><creator>Faluvegi, Agota</creator><creator>Bolsee, Quentin</creator><creator>Nedevschi, Sergiu</creator><creator>Dadarlat, Vasile-Teodor</creator><creator>Munteanu, Adrian</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201912</creationdate><title>A 3D Convolutional Neural Network for Light Field Depth Estimation</title><author>Faluvegi, Agota ; Bolsee, Quentin ; Nedevschi, Sergiu ; Dadarlat, Vasile-Teodor ; Munteanu, Adrian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c256t-d5fbdd28f2125a096c8342d4981979da895aad74fc5164f47db7a06098ff826f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2019</creationdate><topic>3D convolution</topic><topic>CNN</topic><topic>Computer vision</topic><topic>Convolution</topic><topic>Deep learning</topic><topic>depth estimation</topic><topic>disparity map</topic><topic>EPI</topic><topic>Estimation</topic><topic>Focusing</topic><topic>Light field image</topic><topic>Neural networks</topic><topic>Three-dimensional displays</topic><toplevel>online_resources</toplevel><creatorcontrib>Faluvegi, Agota</creatorcontrib><creatorcontrib>Bolsee, Quentin</creatorcontrib><creatorcontrib>Nedevschi, Sergiu</creatorcontrib><creatorcontrib>Dadarlat, Vasile-Teodor</creatorcontrib><creatorcontrib>Munteanu, Adrian</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Faluvegi, Agota</au><au>Bolsee, Quentin</au><au>Nedevschi, Sergiu</au><au>Dadarlat, Vasile-Teodor</au><au>Munteanu, Adrian</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A 3D Convolutional Neural Network for Light Field Depth Estimation</atitle><btitle>2019 International Conference on 3D Immersion (IC3D)</btitle><stitle>IC3D</stitle><date>2019-12</date><risdate>2019</risdate><spage>1</spage><epage>5</epage><pages>1-5</pages><eissn>2379-1780</eissn><eisbn>9781728151892</eisbn><eisbn>1728151899</eisbn><abstract>Depth estimation has always been a great challenge in the field of computer vision and machine learning. There is a rich literature focusing on depth estimation in stereo vision or in monocular imaging, while the domain of depth estimation in light field images is still in its infancy. The paper proposes a fully convolutional 3D neural network that estimates the disparity in light field images. The proposed method is parametric as it is able to adapt to input images of arbitrary size and it is lightweight and less prone to overfitting thanks to its fully convolutional nature. The experiments reveal competitive results against the state of the art, demonstrating the potential offered by deep learning solutions for disparity estimation in light field images.</abstract><pub>IEEE</pub><doi>10.1109/IC3D48390.2019.8975996</doi><tpages>5</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | EISSN: 2379-1780 |
| ispartof | 2019 International Conference on 3D Immersion (IC3D), 2019, p.1-5 |
| issn | 2379-1780 |
| language | eng |
| recordid | cdi_ieee_primary_8975996 |
| source | IEEE Xplore All Conference Series |
| subjects | 3D convolution CNN Computer vision Convolution Deep learning depth estimation disparity map EPI Estimation Focusing Light field image Neural networks Three-dimensional displays |
| title | A 3D Convolutional Neural Network for Light Field Depth Estimation |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T00%3A58%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=A%203D%20Convolutional%20Neural%20Network%20for%20Light%20Field%20Depth%20Estimation&rft.btitle=2019%20International%20Conference%20on%203D%20Immersion%20(IC3D)&rft.au=Faluvegi,%20Agota&rft.date=2019-12&rft.spage=1&rft.epage=5&rft.pages=1-5&rft.eissn=2379-1780&rft_id=info:doi/10.1109/IC3D48390.2019.8975996&rft.eisbn=9781728151892&rft.eisbn_list=1728151899&rft_dat=%3Cieee_CHZPO%3E8975996%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c256t-d5fbdd28f2125a096c8342d4981979da895aad74fc5164f47db7a06098ff826f3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=8975996&rfr_iscdi=true |