Jan-Niklas Dihlmann, Arjun Majumdar, Andreas Engelhardt, Raphael Braun, Hendrik P. A. Lensch
{"title":"三维高斯溅射的次表层散射","authors":"Jan-Niklas Dihlmann, Arjun Majumdar, Andreas Engelhardt, Raphael Braun, Hendrik P. A. Lensch","doi":"arxiv-2408.12282","DOIUrl":null,"url":null,"abstract":"3D reconstruction and relighting of objects made from scattering materials\npresent a significant challenge due to the complex light transport beneath the\nsurface. 3D Gaussian Splatting introduced high-quality novel view synthesis at\nreal-time speeds. While 3D Gaussians efficiently approximate an object's\nsurface, they fail to capture the volumetric properties of subsurface\nscattering. We propose a framework for optimizing an object's shape together\nwith the radiance transfer field given multi-view OLAT (one light at a time)\ndata. Our method decomposes the scene into an explicit surface represented as\n3D Gaussians, with a spatially varying BRDF, and an implicit volumetric\nrepresentation of the scattering component. A learned incident light field\naccounts for shadowing. We optimize all parameters jointly via ray-traced\ndifferentiable rendering. Our approach enables material editing, relighting and\nnovel view synthesis at interactive rates. We show successful application on\nsynthetic data and introduce a newly acquired multi-view multi-light dataset of\nobjects in a light-stage setup. Compared to previous work we achieve comparable\nor better results at a fraction of optimization and rendering time while\nenabling detailed control over material attributes. Project page\nhttps://sss.jdihlmann.com/","PeriodicalId":501174,"journal":{"name":"arXiv - CS - Graphics","volume":"13 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Subsurface Scattering for 3D Gaussian Splatting\",\"authors\":\"Jan-Niklas Dihlmann, Arjun Majumdar, Andreas Engelhardt, Raphael Braun, Hendrik P. A. Lensch\",\"doi\":\"arxiv-2408.12282\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"3D reconstruction and relighting of objects made from scattering materials\\npresent a significant challenge due to the complex light transport beneath the\\nsurface. 3D Gaussian Splatting introduced high-quality novel view synthesis at\\nreal-time speeds. While 3D Gaussians efficiently approximate an object's\\nsurface, they fail to capture the volumetric properties of subsurface\\nscattering. We propose a framework for optimizing an object's shape together\\nwith the radiance transfer field given multi-view OLAT (one light at a time)\\ndata. Our method decomposes the scene into an explicit surface represented as\\n3D Gaussians, with a spatially varying BRDF, and an implicit volumetric\\nrepresentation of the scattering component. A learned incident light field\\naccounts for shadowing. We optimize all parameters jointly via ray-traced\\ndifferentiable rendering. Our approach enables material editing, relighting and\\nnovel view synthesis at interactive rates. We show successful application on\\nsynthetic data and introduce a newly acquired multi-view multi-light dataset of\\nobjects in a light-stage setup. Compared to previous work we achieve comparable\\nor better results at a fraction of optimization and rendering time while\\nenabling detailed control over material attributes. Project page\\nhttps://sss.jdihlmann.com/\",\"PeriodicalId\":501174,\"journal\":{\"name\":\"arXiv - CS - Graphics\",\"volume\":\"13 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-22\",\"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-2408.12282\",\"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-2408.12282","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
3D reconstruction and relighting of objects made from scattering materials
present a significant challenge due to the complex light transport beneath the
surface. 3D Gaussian Splatting introduced high-quality novel view synthesis at
real-time speeds. While 3D Gaussians efficiently approximate an object's
surface, they fail to capture the volumetric properties of subsurface
scattering. We propose a framework for optimizing an object's shape together
with the radiance transfer field given multi-view OLAT (one light at a time)
data. Our method decomposes the scene into an explicit surface represented as
3D Gaussians, with a spatially varying BRDF, and an implicit volumetric
representation of the scattering component. A learned incident light field
accounts for shadowing. We optimize all parameters jointly via ray-traced
differentiable rendering. Our approach enables material editing, relighting and
novel view synthesis at interactive rates. We show successful application on
synthetic data and introduce a newly acquired multi-view multi-light dataset of
objects in a light-stage setup. Compared to previous work we achieve comparable
or better results at a fraction of optimization and rendering time while
enabling detailed control over material attributes. Project page
https://sss.jdihlmann.com/