Benjamin Attal, Dor Verbin, Ben Mildenhall, Peter Hedman, Jonathan T. Barron, Matthew O'Toole, Pratul P. Srinivasan
{"title":"闪存缓存:减少基于辐射缓存的反渲染中的偏差","authors":"Benjamin Attal, Dor Verbin, Ben Mildenhall, Peter Hedman, Jonathan T. Barron, Matthew O'Toole, Pratul P. Srinivasan","doi":"arxiv-2409.05867","DOIUrl":null,"url":null,"abstract":"State-of-the-art techniques for 3D reconstruction are largely based on\nvolumetric scene representations, which require sampling multiple points to\ncompute the color arriving along a ray. Using these representations for more\ngeneral inverse rendering -- reconstructing geometry, materials, and lighting\nfrom observed images -- is challenging because recursively path-tracing such\nvolumetric representations is expensive. Recent works alleviate this issue\nthrough the use of radiance caches: data structures that store the\nsteady-state, infinite-bounce radiance arriving at any point from any\ndirection. However, these solutions rely on approximations that introduce bias\ninto the renderings and, more importantly, into the gradients used for\noptimization. We present a method that avoids these approximations while\nremaining computationally efficient. In particular, we leverage two techniques\nto reduce variance for unbiased estimators of the rendering equation: (1) an\nocclusion-aware importance sampler for incoming illumination and (2) a fast\ncache architecture that can be used as a control variate for the radiance from\na high-quality, but more expensive, volumetric cache. We show that by removing\nthese biases our approach improves the generality of radiance cache based\ninverse rendering, as well as increasing quality in the presence of challenging\nlight transport effects such as specular reflections.","PeriodicalId":501174,"journal":{"name":"arXiv - CS - Graphics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Flash Cache: Reducing Bias in Radiance Cache Based Inverse Rendering\",\"authors\":\"Benjamin Attal, Dor Verbin, Ben Mildenhall, Peter Hedman, Jonathan T. Barron, Matthew O'Toole, Pratul P. Srinivasan\",\"doi\":\"arxiv-2409.05867\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"State-of-the-art techniques for 3D reconstruction are largely based on\\nvolumetric scene representations, which require sampling multiple points to\\ncompute the color arriving along a ray. Using these representations for more\\ngeneral inverse rendering -- reconstructing geometry, materials, and lighting\\nfrom observed images -- is challenging because recursively path-tracing such\\nvolumetric representations is expensive. Recent works alleviate this issue\\nthrough the use of radiance caches: data structures that store the\\nsteady-state, infinite-bounce radiance arriving at any point from any\\ndirection. However, these solutions rely on approximations that introduce bias\\ninto the renderings and, more importantly, into the gradients used for\\noptimization. We present a method that avoids these approximations while\\nremaining computationally efficient. In particular, we leverage two techniques\\nto reduce variance for unbiased estimators of the rendering equation: (1) an\\nocclusion-aware importance sampler for incoming illumination and (2) a fast\\ncache architecture that can be used as a control variate for the radiance from\\na high-quality, but more expensive, volumetric cache. We show that by removing\\nthese biases our approach improves the generality of radiance cache based\\ninverse rendering, as well as increasing quality in the presence of challenging\\nlight transport effects such as specular reflections.\",\"PeriodicalId\":501174,\"journal\":{\"name\":\"arXiv - CS - Graphics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-09\",\"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-2409.05867\",\"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-2409.05867","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Flash Cache: Reducing Bias in Radiance Cache Based Inverse Rendering
State-of-the-art techniques for 3D reconstruction are largely based on
volumetric scene representations, which require sampling multiple points to
compute the color arriving along a ray. Using these representations for more
general inverse rendering -- reconstructing geometry, materials, and lighting
from observed images -- is challenging because recursively path-tracing such
volumetric representations is expensive. Recent works alleviate this issue
through the use of radiance caches: data structures that store the
steady-state, infinite-bounce radiance arriving at any point from any
direction. However, these solutions rely on approximations that introduce bias
into the renderings and, more importantly, into the gradients used for
optimization. We present a method that avoids these approximations while
remaining computationally efficient. In particular, we leverage two techniques
to reduce variance for unbiased estimators of the rendering equation: (1) an
occlusion-aware importance sampler for incoming illumination and (2) a fast
cache architecture that can be used as a control variate for the radiance from
a high-quality, but more expensive, volumetric cache. We show that by removing
these biases our approach improves the generality of radiance cache based
inverse rendering, as well as increasing quality in the presence of challenging
light transport effects such as specular reflections.