Robust Geometry and Reflectance Disentanglement for 3D Face Reconstruction from Sparse-view Images

This paper presents a novel two-stage approach for reconstructing human faces from sparse-view images, a task made challenging by the unique geometry and complex skin reflectance of each individual. Our method focuses on decomposing key facial attributes, including geometry, diffuse reflectance, and...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jin, Daisheng, Hu, Jiangbei, Xu, Baixin, Dai, Yuxin, Qian, Chen, He, Ying
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 Jin, Daisheng
Hu, Jiangbei
Xu, Baixin
Dai, Yuxin
Qian, Chen
He, Ying
description This paper presents a novel two-stage approach for reconstructing human faces from sparse-view images, a task made challenging by the unique geometry and complex skin reflectance of each individual. Our method focuses on decomposing key facial attributes, including geometry, diffuse reflectance, and specular reflectance, from ambient light. Initially, we create a general facial template from a diverse collection of individual faces, capturing essential geometric and reflectance characteristics. Guided by this template, we refine each specific face model in the second stage, which further considers the interaction between geometry and reflectance, as well as the subsurface scattering effects on facial skin. Our method enables the reconstruction of high-quality facial representations from as few as three images, offering improved geometric accuracy and reflectance detail. Through comprehensive evaluations and comparisons, our method demonstrates superiority over existing techniques. Our method effectively disentangles geometry and reflectance components, leading to enhanced quality in synthesizing new views and opening up possibilities for applications such as relighting and reflectance editing. We will make the code publicly available.
doi_str_mv 10.48550/arxiv.2312.06085
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2312_06085</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2312_06085</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-6d76de2d4e4325a4e8fb053a963167e594c2cc7431e2c2c686897c14327902bf3</originalsourceid><addsrcrecordid>eNotj8tqwzAURLXJoiT9gK6qH7Ar62kvS9KkgUDBzd5cy1dBYFtBctLm7-umXc2BGQYOIU8Fy2WpFHuB-O2vORcFz5lmpXogbR3aS5roDsOAU7xRGDtao-vRTjBapBufcJzx1OMwA3UhUrGhW5i7Gm0Y0xQvdvJhpC6GgX6eISbMrh6_6H6AE6YVWTjoEz7-55Ict2_H9Xt2-Njt16-HDLRRme6M7pB3EqXgCiSWrmVKQKVFoQ2qSlpurZGiQD6TLnVZGVvMY1Mx3jqxJM9_t3fJ5hz9APHW_Mo2d1nxA4CnT3w</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Robust Geometry and Reflectance Disentanglement for 3D Face Reconstruction from Sparse-view Images</title><source>arXiv.org</source><creator>Jin, Daisheng ; Hu, Jiangbei ; Xu, Baixin ; Dai, Yuxin ; Qian, Chen ; He, Ying</creator><creatorcontrib>Jin, Daisheng ; Hu, Jiangbei ; Xu, Baixin ; Dai, Yuxin ; Qian, Chen ; He, Ying</creatorcontrib><description>This paper presents a novel two-stage approach for reconstructing human faces from sparse-view images, a task made challenging by the unique geometry and complex skin reflectance of each individual. Our method focuses on decomposing key facial attributes, including geometry, diffuse reflectance, and specular reflectance, from ambient light. Initially, we create a general facial template from a diverse collection of individual faces, capturing essential geometric and reflectance characteristics. Guided by this template, we refine each specific face model in the second stage, which further considers the interaction between geometry and reflectance, as well as the subsurface scattering effects on facial skin. Our method enables the reconstruction of high-quality facial representations from as few as three images, offering improved geometric accuracy and reflectance detail. Through comprehensive evaluations and comparisons, our method demonstrates superiority over existing techniques. Our method effectively disentangles geometry and reflectance components, leading to enhanced quality in synthesizing new views and opening up possibilities for applications such as relighting and reflectance editing. We will make the code publicly available.</description><identifier>DOI: 10.48550/arxiv.2312.06085</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2023-12</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</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/2312.06085$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2312.06085$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Jin, Daisheng</creatorcontrib><creatorcontrib>Hu, Jiangbei</creatorcontrib><creatorcontrib>Xu, Baixin</creatorcontrib><creatorcontrib>Dai, Yuxin</creatorcontrib><creatorcontrib>Qian, Chen</creatorcontrib><creatorcontrib>He, Ying</creatorcontrib><title>Robust Geometry and Reflectance Disentanglement for 3D Face Reconstruction from Sparse-view Images</title><description>This paper presents a novel two-stage approach for reconstructing human faces from sparse-view images, a task made challenging by the unique geometry and complex skin reflectance of each individual. Our method focuses on decomposing key facial attributes, including geometry, diffuse reflectance, and specular reflectance, from ambient light. Initially, we create a general facial template from a diverse collection of individual faces, capturing essential geometric and reflectance characteristics. Guided by this template, we refine each specific face model in the second stage, which further considers the interaction between geometry and reflectance, as well as the subsurface scattering effects on facial skin. Our method enables the reconstruction of high-quality facial representations from as few as three images, offering improved geometric accuracy and reflectance detail. Through comprehensive evaluations and comparisons, our method demonstrates superiority over existing techniques. Our method effectively disentangles geometry and reflectance components, leading to enhanced quality in synthesizing new views and opening up possibilities for applications such as relighting and reflectance editing. We will make the code publicly available.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tqwzAURLXJoiT9gK6qH7Ar62kvS9KkgUDBzd5cy1dBYFtBctLm7-umXc2BGQYOIU8Fy2WpFHuB-O2vORcFz5lmpXogbR3aS5roDsOAU7xRGDtao-vRTjBapBufcJzx1OMwA3UhUrGhW5i7Gm0Y0xQvdvJhpC6GgX6eISbMrh6_6H6AE6YVWTjoEz7-55Ict2_H9Xt2-Njt16-HDLRRme6M7pB3EqXgCiSWrmVKQKVFoQ2qSlpurZGiQD6TLnVZGVvMY1Mx3jqxJM9_t3fJ5hz9APHW_Mo2d1nxA4CnT3w</recordid><startdate>20231210</startdate><enddate>20231210</enddate><creator>Jin, Daisheng</creator><creator>Hu, Jiangbei</creator><creator>Xu, Baixin</creator><creator>Dai, Yuxin</creator><creator>Qian, Chen</creator><creator>He, Ying</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20231210</creationdate><title>Robust Geometry and Reflectance Disentanglement for 3D Face Reconstruction from Sparse-view Images</title><author>Jin, Daisheng ; Hu, Jiangbei ; Xu, Baixin ; Dai, Yuxin ; Qian, Chen ; He, Ying</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-6d76de2d4e4325a4e8fb053a963167e594c2cc7431e2c2c686897c14327902bf3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Jin, Daisheng</creatorcontrib><creatorcontrib>Hu, Jiangbei</creatorcontrib><creatorcontrib>Xu, Baixin</creatorcontrib><creatorcontrib>Dai, Yuxin</creatorcontrib><creatorcontrib>Qian, Chen</creatorcontrib><creatorcontrib>He, Ying</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Jin, Daisheng</au><au>Hu, Jiangbei</au><au>Xu, Baixin</au><au>Dai, Yuxin</au><au>Qian, Chen</au><au>He, Ying</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Robust Geometry and Reflectance Disentanglement for 3D Face Reconstruction from Sparse-view Images</atitle><date>2023-12-10</date><risdate>2023</risdate><abstract>This paper presents a novel two-stage approach for reconstructing human faces from sparse-view images, a task made challenging by the unique geometry and complex skin reflectance of each individual. Our method focuses on decomposing key facial attributes, including geometry, diffuse reflectance, and specular reflectance, from ambient light. Initially, we create a general facial template from a diverse collection of individual faces, capturing essential geometric and reflectance characteristics. Guided by this template, we refine each specific face model in the second stage, which further considers the interaction between geometry and reflectance, as well as the subsurface scattering effects on facial skin. Our method enables the reconstruction of high-quality facial representations from as few as three images, offering improved geometric accuracy and reflectance detail. Through comprehensive evaluations and comparisons, our method demonstrates superiority over existing techniques. Our method effectively disentangles geometry and reflectance components, leading to enhanced quality in synthesizing new views and opening up possibilities for applications such as relighting and reflectance editing. We will make the code publicly available.</abstract><doi>10.48550/arxiv.2312.06085</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2312.06085
ispartof
issn
language eng
recordid cdi_arxiv_primary_2312_06085
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title Robust Geometry and Reflectance Disentanglement for 3D Face Reconstruction from Sparse-view Images
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T08%3A00%3A17IST&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=Robust%20Geometry%20and%20Reflectance%20Disentanglement%20for%203D%20Face%20Reconstruction%20from%20Sparse-view%20Images&rft.au=Jin,%20Daisheng&rft.date=2023-12-10&rft_id=info:doi/10.48550/arxiv.2312.06085&rft_dat=%3Carxiv_GOX%3E2312_06085%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