Yuxiao Zhou, Menglei Chai, Daoye Wang, Sebastian Winberg, Erroll Wood, Kripasindhu Sarkar, Markus Gross, Thabo Beeler
{"title":"GroomCap:高保真无前发捕捉功能","authors":"Yuxiao Zhou, Menglei Chai, Daoye Wang, Sebastian Winberg, Erroll Wood, Kripasindhu Sarkar, Markus Gross, Thabo Beeler","doi":"arxiv-2409.00831","DOIUrl":null,"url":null,"abstract":"Despite recent advances in multi-view hair reconstruction, achieving\nstrand-level precision remains a significant challenge due to inherent\nlimitations in existing capture pipelines. We introduce GroomCap, a novel\nmulti-view hair capture method that reconstructs faithful and high-fidelity\nhair geometry without relying on external data priors. To address the\nlimitations of conventional reconstruction algorithms, we propose a neural\nimplicit representation for hair volume that encodes high-resolution 3D\norientation and occupancy from input views. This implicit hair volume is\ntrained with a new volumetric 3D orientation rendering algorithm, coupled with\n2D orientation distribution supervision, to effectively prevent the loss of\nstructural information caused by undesired orientation blending. We further\npropose a Gaussian-based hair optimization strategy to refine the traced hair\nstrands with a novel chained Gaussian representation, utilizing direct\nphotometric supervision from images. Our results demonstrate that GroomCap is\nable to capture high-quality hair geometries that are not only more precise and\ndetailed than existing methods but also versatile enough for a range of\napplications.","PeriodicalId":501174,"journal":{"name":"arXiv - CS - Graphics","volume":"22 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"GroomCap: High-Fidelity Prior-Free Hair Capture\",\"authors\":\"Yuxiao Zhou, Menglei Chai, Daoye Wang, Sebastian Winberg, Erroll Wood, Kripasindhu Sarkar, Markus Gross, Thabo Beeler\",\"doi\":\"arxiv-2409.00831\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Despite recent advances in multi-view hair reconstruction, achieving\\nstrand-level precision remains a significant challenge due to inherent\\nlimitations in existing capture pipelines. We introduce GroomCap, a novel\\nmulti-view hair capture method that reconstructs faithful and high-fidelity\\nhair geometry without relying on external data priors. To address the\\nlimitations of conventional reconstruction algorithms, we propose a neural\\nimplicit representation for hair volume that encodes high-resolution 3D\\norientation and occupancy from input views. This implicit hair volume is\\ntrained with a new volumetric 3D orientation rendering algorithm, coupled with\\n2D orientation distribution supervision, to effectively prevent the loss of\\nstructural information caused by undesired orientation blending. We further\\npropose a Gaussian-based hair optimization strategy to refine the traced hair\\nstrands with a novel chained Gaussian representation, utilizing direct\\nphotometric supervision from images. Our results demonstrate that GroomCap is\\nable to capture high-quality hair geometries that are not only more precise and\\ndetailed than existing methods but also versatile enough for a range of\\napplications.\",\"PeriodicalId\":501174,\"journal\":{\"name\":\"arXiv - CS - Graphics\",\"volume\":\"22 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Graphics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.00831\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Graphics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.00831","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Despite recent advances in multi-view hair reconstruction, achieving
strand-level precision remains a significant challenge due to inherent
limitations in existing capture pipelines. We introduce GroomCap, a novel
multi-view hair capture method that reconstructs faithful and high-fidelity
hair geometry without relying on external data priors. To address the
limitations of conventional reconstruction algorithms, we propose a neural
implicit representation for hair volume that encodes high-resolution 3D
orientation and occupancy from input views. This implicit hair volume is
trained with a new volumetric 3D orientation rendering algorithm, coupled with
2D orientation distribution supervision, to effectively prevent the loss of
structural information caused by undesired orientation blending. We further
propose a Gaussian-based hair optimization strategy to refine the traced hair
strands with a novel chained Gaussian representation, utilizing direct
photometric supervision from images. Our results demonstrate that GroomCap is
able to capture high-quality hair geometries that are not only more precise and
detailed than existing methods but also versatile enough for a range of
applications.