Super-resolution 3D Human Shape from a Single Low-Resolution Image

We propose a novel framework to reconstruct super-resolution human shape from a single low-resolution input image. The approach overcomes limitations of existing approaches that reconstruct 3D human shape from a single image, which require high-resolution images together with auxiliary data such as...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pesavento, Marco, Volino, Marco, Hilton, Adrian
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Pesavento, Marco
Volino, Marco
Hilton, Adrian
description We propose a novel framework to reconstruct super-resolution human shape from a single low-resolution input image. The approach overcomes limitations of existing approaches that reconstruct 3D human shape from a single image, which require high-resolution images together with auxiliary data such as surface normal or a parametric model to reconstruct high-detail shape. The proposed framework represents the reconstructed shape with a high-detail implicit function. Analogous to the objective of 2D image super-resolution, the approach learns the mapping from a low-resolution shape to its high-resolution counterpart and it is applied to reconstruct 3D shape detail from low-resolution images. The approach is trained end-to-end employing a novel loss function which estimates the information lost between a low and high-resolution representation of the same 3D surface shape. Evaluation for single image reconstruction of clothed people demonstrates that our method achieves high-detail surface reconstruction from low-resolution images without auxiliary data. Extensive experiments show that the proposed approach can estimate super-resolution human geometries with a significantly higher level of detail than that obtained with previous approaches when applied to low-resolution images.
doi_str_mv 10.48550/arxiv.2208.10738
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2208_10738</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2208_10738</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-db9f9a039f0e1c2759ff8d327b89b8ebfc4544d756133833f4a0919b37bbb51d3</originalsourceid><addsrcrecordid>eNpFz71uwjAYhWEvDAh6AUz1DTi189nYHiktJVIkpIY9-kxsiJQ_maald181rcR0lldHeghZCZ5IoxR_wnirP5M05SYRXIOZk-diHHxk0V_7Zvyo-47CC92PLXa0uODgaYh9S5EWdXduPM37L_Z-b7MWz35JZgGbq3_43wU57l6P2z3LD2_ZdpMzXGvDKmeDRQ42cC9OqVY2BFNBqp2xzngXTlJJWWm1FgAGIEjkVlgH2jmnRAUL8vh3OyHKIdYtxu_yF1NOGPgBPgtDvw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Super-resolution 3D Human Shape from a Single Low-Resolution Image</title><source>arXiv.org</source><creator>Pesavento, Marco ; Volino, Marco ; Hilton, Adrian</creator><creatorcontrib>Pesavento, Marco ; Volino, Marco ; Hilton, Adrian</creatorcontrib><description>We propose a novel framework to reconstruct super-resolution human shape from a single low-resolution input image. The approach overcomes limitations of existing approaches that reconstruct 3D human shape from a single image, which require high-resolution images together with auxiliary data such as surface normal or a parametric model to reconstruct high-detail shape. The proposed framework represents the reconstructed shape with a high-detail implicit function. Analogous to the objective of 2D image super-resolution, the approach learns the mapping from a low-resolution shape to its high-resolution counterpart and it is applied to reconstruct 3D shape detail from low-resolution images. The approach is trained end-to-end employing a novel loss function which estimates the information lost between a low and high-resolution representation of the same 3D surface shape. Evaluation for single image reconstruction of clothed people demonstrates that our method achieves high-detail surface reconstruction from low-resolution images without auxiliary data. Extensive experiments show that the proposed approach can estimate super-resolution human geometries with a significantly higher level of detail than that obtained with previous approaches when applied to low-resolution images.</description><identifier>DOI: 10.48550/arxiv.2208.10738</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2022-08</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2208.10738$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2208.10738$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Pesavento, Marco</creatorcontrib><creatorcontrib>Volino, Marco</creatorcontrib><creatorcontrib>Hilton, Adrian</creatorcontrib><title>Super-resolution 3D Human Shape from a Single Low-Resolution Image</title><description>We propose a novel framework to reconstruct super-resolution human shape from a single low-resolution input image. The approach overcomes limitations of existing approaches that reconstruct 3D human shape from a single image, which require high-resolution images together with auxiliary data such as surface normal or a parametric model to reconstruct high-detail shape. The proposed framework represents the reconstructed shape with a high-detail implicit function. Analogous to the objective of 2D image super-resolution, the approach learns the mapping from a low-resolution shape to its high-resolution counterpart and it is applied to reconstruct 3D shape detail from low-resolution images. The approach is trained end-to-end employing a novel loss function which estimates the information lost between a low and high-resolution representation of the same 3D surface shape. Evaluation for single image reconstruction of clothed people demonstrates that our method achieves high-detail surface reconstruction from low-resolution images without auxiliary data. Extensive experiments show that the proposed approach can estimate super-resolution human geometries with a significantly higher level of detail than that obtained with previous approaches when applied to low-resolution images.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpFz71uwjAYhWEvDAh6AUz1DTi189nYHiktJVIkpIY9-kxsiJQ_maald181rcR0lldHeghZCZ5IoxR_wnirP5M05SYRXIOZk-diHHxk0V_7Zvyo-47CC92PLXa0uODgaYh9S5EWdXduPM37L_Z-b7MWz35JZgGbq3_43wU57l6P2z3LD2_ZdpMzXGvDKmeDRQ42cC9OqVY2BFNBqp2xzngXTlJJWWm1FgAGIEjkVlgH2jmnRAUL8vh3OyHKIdYtxu_yF1NOGPgBPgtDvw</recordid><startdate>20220823</startdate><enddate>20220823</enddate><creator>Pesavento, Marco</creator><creator>Volino, Marco</creator><creator>Hilton, Adrian</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220823</creationdate><title>Super-resolution 3D Human Shape from a Single Low-Resolution Image</title><author>Pesavento, Marco ; Volino, Marco ; Hilton, Adrian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-db9f9a039f0e1c2759ff8d327b89b8ebfc4544d756133833f4a0919b37bbb51d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Pesavento, Marco</creatorcontrib><creatorcontrib>Volino, Marco</creatorcontrib><creatorcontrib>Hilton, Adrian</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Pesavento, Marco</au><au>Volino, Marco</au><au>Hilton, Adrian</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Super-resolution 3D Human Shape from a Single Low-Resolution Image</atitle><date>2022-08-23</date><risdate>2022</risdate><abstract>We propose a novel framework to reconstruct super-resolution human shape from a single low-resolution input image. The approach overcomes limitations of existing approaches that reconstruct 3D human shape from a single image, which require high-resolution images together with auxiliary data such as surface normal or a parametric model to reconstruct high-detail shape. The proposed framework represents the reconstructed shape with a high-detail implicit function. Analogous to the objective of 2D image super-resolution, the approach learns the mapping from a low-resolution shape to its high-resolution counterpart and it is applied to reconstruct 3D shape detail from low-resolution images. The approach is trained end-to-end employing a novel loss function which estimates the information lost between a low and high-resolution representation of the same 3D surface shape. Evaluation for single image reconstruction of clothed people demonstrates that our method achieves high-detail surface reconstruction from low-resolution images without auxiliary data. Extensive experiments show that the proposed approach can estimate super-resolution human geometries with a significantly higher level of detail than that obtained with previous approaches when applied to low-resolution images.</abstract><doi>10.48550/arxiv.2208.10738</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2208.10738
ispartof
issn
language eng
recordid cdi_arxiv_primary_2208_10738
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title Super-resolution 3D Human Shape from a Single Low-Resolution Image
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T01%3A42%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Super-resolution%203D%20Human%20Shape%20from%20a%20Single%20Low-Resolution%20Image&rft.au=Pesavento,%20Marco&rft.date=2022-08-23&rft_id=info:doi/10.48550/arxiv.2208.10738&rft_dat=%3Carxiv_GOX%3E2208_10738%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true