Loading…
Low-Rank Matrix Completion to Reconstruct Incomplete Rendering Images
Path tracing provides photo-realistic rendering in many applications but intermediate previsualization often suffers from distracting noise. Since the fundamental underlying problem is insufficient samples, we exploit the coherence of the visual signal to reconstruct missing samples, using a low-ran...
Saved in:
| Published in: | IEEE transactions on visualization and computer graphics 2018-08, Vol.24 (8), p.2353-2365 |
|---|---|
| Main Authors: | , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| Citations: | Items that this one cites Items that cite this one |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | cdi_FETCH-LOGICAL-c349t-820ccf19f3e8f01772b4c42da13f7d8ba529be1a27109f569c6ec7f6f986a37d3 |
|---|---|
| cites | cdi_FETCH-LOGICAL-c349t-820ccf19f3e8f01772b4c42da13f7d8ba529be1a27109f569c6ec7f6f986a37d3 |
| container_end_page | 2365 |
| container_issue | 8 |
| container_start_page | 2353 |
| container_title | IEEE transactions on visualization and computer graphics |
| container_volume | 24 |
| creator | Liu, Ping Lewis, John Rhee, Taehyun |
| description | Path tracing provides photo-realistic rendering in many applications but intermediate previsualization often suffers from distracting noise. Since the fundamental underlying problem is insufficient samples, we exploit the coherence of the visual signal to reconstruct missing samples, using a low-rank matrix completion framework. We present novel methods to construct low rank matrices for incomplete images including missing pixel, missing sub-pixel, and multi-frame scenarios. A convolutional neural network provides fast pre-completion for initialising missing values, and subsequent weighted nuclear norm minimisation (WNNM) with a parameter adjustment strategy (PAWNNM) efficiently recovers missing values even in high frequency details. The result shows better visual quality than recent methods including compressed sensing based reconstruction. |
| doi_str_mv | 10.1109/TVCG.2017.2722414 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_proquest_journals_2063043262</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7967887</ieee_id><sourcerecordid>1917965901</sourcerecordid><originalsourceid>FETCH-LOGICAL-c349t-820ccf19f3e8f01772b4c42da13f7d8ba529be1a27109f569c6ec7f6f986a37d3</originalsourceid><addsrcrecordid>eNpdkMFKAzEQhoMotlYfQARZ8OJla5JNk81RlloLFaFUryHNTsrW7qYmu6hvb0prD54mzHwz_PkQuiZ4SAiWD4v3YjKkmIghFZQywk5Qn0hGUjzC_DS-sRAp5ZT30EUIa4wJY7k8Rz2ac0mlEH00nrmvdK6bj-RFt776TgpXbzfQVq5JWpfMwbgmtL4zbTJtzH4Gsd2U4KtmlUxrvYJwic6s3gS4OtQBensaL4rndPY6mRaPs9RkTLZpTrExlkibQW5jbEGXzDBaapJZUeZLPaJyCURTEX9nR1waDkZYbmXOdSbKbIDu93e33n12EFpVV8HAZqMbcF1QRBIh-UhiEtG7f-jadb6J6RTFPMMsi2IiRfaU8S4ED1ZtfVVr_6MIVjvHaudY7Ryrg-O4c3u43C1rKI8bf1IjcLMHKgA4jmMwkeci-wVVUH8O</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2063043262</pqid></control><display><type>article</type><title>Low-Rank Matrix Completion to Reconstruct Incomplete Rendering Images</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Liu, Ping ; Lewis, John ; Rhee, Taehyun</creator><creatorcontrib>Liu, Ping ; Lewis, John ; Rhee, Taehyun</creatorcontrib><description>Path tracing provides photo-realistic rendering in many applications but intermediate previsualization often suffers from distracting noise. Since the fundamental underlying problem is insufficient samples, we exploit the coherence of the visual signal to reconstruct missing samples, using a low-rank matrix completion framework. We present novel methods to construct low rank matrices for incomplete images including missing pixel, missing sub-pixel, and multi-frame scenarios. A convolutional neural network provides fast pre-completion for initialising missing values, and subsequent weighted nuclear norm minimisation (WNNM) with a parameter adjustment strategy (PAWNNM) efficiently recovers missing values even in high frequency details. The result shows better visual quality than recent methods including compressed sensing based reconstruction.</description><identifier>ISSN: 1077-2626</identifier><identifier>EISSN: 1941-0506</identifier><identifier>DOI: 10.1109/TVCG.2017.2722414</identifier><identifier>PMID: 28692977</identifier><identifier>CODEN: ITVGEA</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Artificial neural networks ; convolutional neural network ; Image coding ; Image reconstruction ; matrix completion ; Minimization ; Monte Carlo methods ; Neural networks ; nuclear norm minimization ; path-tracing ; Pixels ; Previsualisation ; Rendering ; Rendering (computer graphics) ; sampling and reconstruction ; Visual signals ; Visualization</subject><ispartof>IEEE transactions on visualization and computer graphics, 2018-08, Vol.24 (8), p.2353-2365</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c349t-820ccf19f3e8f01772b4c42da13f7d8ba529be1a27109f569c6ec7f6f986a37d3</citedby><cites>FETCH-LOGICAL-c349t-820ccf19f3e8f01772b4c42da13f7d8ba529be1a27109f569c6ec7f6f986a37d3</cites><orcidid>0000-0002-6150-0637</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7967887$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,27923,27924,54795</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/28692977$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Liu, Ping</creatorcontrib><creatorcontrib>Lewis, John</creatorcontrib><creatorcontrib>Rhee, Taehyun</creatorcontrib><title>Low-Rank Matrix Completion to Reconstruct Incomplete Rendering Images</title><title>IEEE transactions on visualization and computer graphics</title><addtitle>TVCG</addtitle><addtitle>IEEE Trans Vis Comput Graph</addtitle><description>Path tracing provides photo-realistic rendering in many applications but intermediate previsualization often suffers from distracting noise. Since the fundamental underlying problem is insufficient samples, we exploit the coherence of the visual signal to reconstruct missing samples, using a low-rank matrix completion framework. We present novel methods to construct low rank matrices for incomplete images including missing pixel, missing sub-pixel, and multi-frame scenarios. A convolutional neural network provides fast pre-completion for initialising missing values, and subsequent weighted nuclear norm minimisation (WNNM) with a parameter adjustment strategy (PAWNNM) efficiently recovers missing values even in high frequency details. The result shows better visual quality than recent methods including compressed sensing based reconstruction.</description><subject>Artificial neural networks</subject><subject>convolutional neural network</subject><subject>Image coding</subject><subject>Image reconstruction</subject><subject>matrix completion</subject><subject>Minimization</subject><subject>Monte Carlo methods</subject><subject>Neural networks</subject><subject>nuclear norm minimization</subject><subject>path-tracing</subject><subject>Pixels</subject><subject>Previsualisation</subject><subject>Rendering</subject><subject>Rendering (computer graphics)</subject><subject>sampling and reconstruction</subject><subject>Visual signals</subject><subject>Visualization</subject><issn>1077-2626</issn><issn>1941-0506</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><recordid>eNpdkMFKAzEQhoMotlYfQARZ8OJla5JNk81RlloLFaFUryHNTsrW7qYmu6hvb0prD54mzHwz_PkQuiZ4SAiWD4v3YjKkmIghFZQywk5Qn0hGUjzC_DS-sRAp5ZT30EUIa4wJY7k8Rz2ac0mlEH00nrmvdK6bj-RFt776TgpXbzfQVq5JWpfMwbgmtL4zbTJtzH4Gsd2U4KtmlUxrvYJwic6s3gS4OtQBensaL4rndPY6mRaPs9RkTLZpTrExlkibQW5jbEGXzDBaapJZUeZLPaJyCURTEX9nR1waDkZYbmXOdSbKbIDu93e33n12EFpVV8HAZqMbcF1QRBIh-UhiEtG7f-jadb6J6RTFPMMsi2IiRfaU8S4ED1ZtfVVr_6MIVjvHaudY7Ryrg-O4c3u43C1rKI8bf1IjcLMHKgA4jmMwkeci-wVVUH8O</recordid><startdate>20180801</startdate><enddate>20180801</enddate><creator>Liu, Ping</creator><creator>Lewis, John</creator><creator>Rhee, Taehyun</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-6150-0637</orcidid></search><sort><creationdate>20180801</creationdate><title>Low-Rank Matrix Completion to Reconstruct Incomplete Rendering Images</title><author>Liu, Ping ; Lewis, John ; Rhee, Taehyun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c349t-820ccf19f3e8f01772b4c42da13f7d8ba529be1a27109f569c6ec7f6f986a37d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Artificial neural networks</topic><topic>convolutional neural network</topic><topic>Image coding</topic><topic>Image reconstruction</topic><topic>matrix completion</topic><topic>Minimization</topic><topic>Monte Carlo methods</topic><topic>Neural networks</topic><topic>nuclear norm minimization</topic><topic>path-tracing</topic><topic>Pixels</topic><topic>Previsualisation</topic><topic>Rendering</topic><topic>Rendering (computer graphics)</topic><topic>sampling and reconstruction</topic><topic>Visual signals</topic><topic>Visualization</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Liu, Ping</creatorcontrib><creatorcontrib>Lewis, John</creatorcontrib><creatorcontrib>Rhee, Taehyun</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on visualization and computer graphics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Liu, Ping</au><au>Lewis, John</au><au>Rhee, Taehyun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Low-Rank Matrix Completion to Reconstruct Incomplete Rendering Images</atitle><jtitle>IEEE transactions on visualization and computer graphics</jtitle><stitle>TVCG</stitle><addtitle>IEEE Trans Vis Comput Graph</addtitle><date>2018-08-01</date><risdate>2018</risdate><volume>24</volume><issue>8</issue><spage>2353</spage><epage>2365</epage><pages>2353-2365</pages><issn>1077-2626</issn><eissn>1941-0506</eissn><coden>ITVGEA</coden><abstract>Path tracing provides photo-realistic rendering in many applications but intermediate previsualization often suffers from distracting noise. Since the fundamental underlying problem is insufficient samples, we exploit the coherence of the visual signal to reconstruct missing samples, using a low-rank matrix completion framework. We present novel methods to construct low rank matrices for incomplete images including missing pixel, missing sub-pixel, and multi-frame scenarios. A convolutional neural network provides fast pre-completion for initialising missing values, and subsequent weighted nuclear norm minimisation (WNNM) with a parameter adjustment strategy (PAWNNM) efficiently recovers missing values even in high frequency details. The result shows better visual quality than recent methods including compressed sensing based reconstruction.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>28692977</pmid><doi>10.1109/TVCG.2017.2722414</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0002-6150-0637</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1077-2626 |
| ispartof | IEEE transactions on visualization and computer graphics, 2018-08, Vol.24 (8), p.2353-2365 |
| issn | 1077-2626 1941-0506 |
| language | eng |
| recordid | cdi_proquest_journals_2063043262 |
| source | IEEE Electronic Library (IEL) Journals |
| subjects | Artificial neural networks convolutional neural network Image coding Image reconstruction matrix completion Minimization Monte Carlo methods Neural networks nuclear norm minimization path-tracing Pixels Previsualisation Rendering Rendering (computer graphics) sampling and reconstruction Visual signals Visualization |
| title | Low-Rank Matrix Completion to Reconstruct Incomplete Rendering Images |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T03%3A58%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Low-Rank%20Matrix%20Completion%20to%20Reconstruct%20Incomplete%20Rendering%20Images&rft.jtitle=IEEE%20transactions%20on%20visualization%20and%20computer%20graphics&rft.au=Liu,%20Ping&rft.date=2018-08-01&rft.volume=24&rft.issue=8&rft.spage=2353&rft.epage=2365&rft.pages=2353-2365&rft.issn=1077-2626&rft.eissn=1941-0506&rft.coden=ITVGEA&rft_id=info:doi/10.1109/TVCG.2017.2722414&rft_dat=%3Cproquest_pubme%3E1917965901%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c349t-820ccf19f3e8f01772b4c42da13f7d8ba529be1a27109f569c6ec7f6f986a37d3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2063043262&rft_id=info:pmid/28692977&rft_ieee_id=7967887&rfr_iscdi=true |