{"title":"用于可变渲染的条件混合路径引导","authors":"Zhimin Fan, Pengcheng Shi, Mufan Guo, Ruoyu Fu, Yanwen Guo, Jie Guo","doi":"10.1145/3658133","DOIUrl":null,"url":null,"abstract":"The efficiency of inverse optimization in physically based differentiable rendering heavily depends on the variance of Monte Carlo estimation. Despite recent advancements emphasizing the necessity of tailored differential sampling strategies, the general approaches remain unexplored.\n In this paper, we investigate the interplay between local sampling decisions and the estimation of light path derivatives. Considering that modern differentiable rendering algorithms share the same path for estimating differential radiance and ordinary radiance, we demonstrate that conventional guiding approaches, conditioned solely on the last vertex, cannot attain this density. Instead, a mixture of different sampling distributions is required, where the weights are conditioned on all the previously sampled vertices in the path. To embody our theory, we implement a conditional mixture path guiding that explicitly computes optimal weights on the fly. Furthermore, we show how to perform positivization to eliminate sign variance and extend to scenes with millions of parameters.\n To the best of our knowledge, this is the first generic framework for applying path guiding to differentiable rendering. Extensive experiments demonstrate that our method achieves nearly one order of magnitude improvements over state-of-the-art methods in terms of variance reduction in gradient estimation and errors of inverse optimization. The implementation of our proposed method is available at https://github.com/mollnn/conditional-mixture.","PeriodicalId":7,"journal":{"name":"ACS Applied Polymer Materials","volume":"123 37","pages":""},"PeriodicalIF":4.4000,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Conditional Mixture Path Guiding for Differentiable Rendering\",\"authors\":\"Zhimin Fan, Pengcheng Shi, Mufan Guo, Ruoyu Fu, Yanwen Guo, Jie Guo\",\"doi\":\"10.1145/3658133\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The efficiency of inverse optimization in physically based differentiable rendering heavily depends on the variance of Monte Carlo estimation. Despite recent advancements emphasizing the necessity of tailored differential sampling strategies, the general approaches remain unexplored.\\n In this paper, we investigate the interplay between local sampling decisions and the estimation of light path derivatives. Considering that modern differentiable rendering algorithms share the same path for estimating differential radiance and ordinary radiance, we demonstrate that conventional guiding approaches, conditioned solely on the last vertex, cannot attain this density. Instead, a mixture of different sampling distributions is required, where the weights are conditioned on all the previously sampled vertices in the path. To embody our theory, we implement a conditional mixture path guiding that explicitly computes optimal weights on the fly. Furthermore, we show how to perform positivization to eliminate sign variance and extend to scenes with millions of parameters.\\n To the best of our knowledge, this is the first generic framework for applying path guiding to differentiable rendering. Extensive experiments demonstrate that our method achieves nearly one order of magnitude improvements over state-of-the-art methods in terms of variance reduction in gradient estimation and errors of inverse optimization. The implementation of our proposed method is available at https://github.com/mollnn/conditional-mixture.\",\"PeriodicalId\":7,\"journal\":{\"name\":\"ACS Applied Polymer Materials\",\"volume\":\"123 37\",\"pages\":\"\"},\"PeriodicalIF\":4.4000,\"publicationDate\":\"2024-07-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACS Applied Polymer Materials\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1145/3658133\",\"RegionNum\":2,\"RegionCategory\":\"化学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"MATERIALS SCIENCE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Applied Polymer Materials","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1145/3658133","RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
Conditional Mixture Path Guiding for Differentiable Rendering
The efficiency of inverse optimization in physically based differentiable rendering heavily depends on the variance of Monte Carlo estimation. Despite recent advancements emphasizing the necessity of tailored differential sampling strategies, the general approaches remain unexplored.
In this paper, we investigate the interplay between local sampling decisions and the estimation of light path derivatives. Considering that modern differentiable rendering algorithms share the same path for estimating differential radiance and ordinary radiance, we demonstrate that conventional guiding approaches, conditioned solely on the last vertex, cannot attain this density. Instead, a mixture of different sampling distributions is required, where the weights are conditioned on all the previously sampled vertices in the path. To embody our theory, we implement a conditional mixture path guiding that explicitly computes optimal weights on the fly. Furthermore, we show how to perform positivization to eliminate sign variance and extend to scenes with millions of parameters.
To the best of our knowledge, this is the first generic framework for applying path guiding to differentiable rendering. Extensive experiments demonstrate that our method achieves nearly one order of magnitude improvements over state-of-the-art methods in terms of variance reduction in gradient estimation and errors of inverse optimization. The implementation of our proposed method is available at https://github.com/mollnn/conditional-mixture.
期刊介绍:
ACS Applied Polymer Materials is an interdisciplinary journal publishing original research covering all aspects of engineering, chemistry, physics, and biology relevant to applications of polymers.
The journal is devoted to reports of new and original experimental and theoretical research of an applied nature that integrates fundamental knowledge in the areas of materials, engineering, physics, bioscience, polymer science and chemistry into important polymer applications. The journal is specifically interested in work that addresses relationships among structure, processing, morphology, chemistry, properties, and function as well as work that provide insights into mechanisms critical to the performance of the polymer for applications.