用于可重光和可交互面部渲染的即时面部高斯转换器

Dafei Qin, Hongyang Lin, Qixuan Zhang, Kaichun Qiao, Longwen Zhang, Zijun Zhao, Jun Saito, Jingyi Yu, Lan Xu, Taku Komura
{"title":"用于可重光和可交互面部渲染的即时面部高斯转换器","authors":"Dafei Qin, Hongyang Lin, Qixuan Zhang, Kaichun Qiao, Longwen Zhang, Zijun Zhao, Jun Saito, Jingyi Yu, Lan Xu, Taku Komura","doi":"arxiv-2409.07441","DOIUrl":null,"url":null,"abstract":"We propose GauFace, a novel Gaussian Splatting representation, tailored for\nefficient animation and rendering of physically-based facial assets. Leveraging\nstrong geometric priors and constrained optimization, GauFace ensures a neat\nand structured Gaussian representation, delivering high fidelity and real-time\nfacial interaction of 30fps@1440p on a Snapdragon 8 Gen 2 mobile platform. Then, we introduce TransGS, a diffusion transformer that instantly translates\nphysically-based facial assets into the corresponding GauFace representations.\nSpecifically, we adopt a patch-based pipeline to handle the vast number of\nGaussians effectively. We also introduce a novel pixel-aligned sampling scheme\nwith UV positional encoding to ensure the throughput and rendering quality of\nGauFace assets generated by our TransGS. Once trained, TransGS can instantly\ntranslate facial assets with lighting conditions to GauFace representation,\nWith the rich conditioning modalities, it also enables editing and animation\ncapabilities reminiscent of traditional CG pipelines. We conduct extensive evaluations and user studies, compared to traditional\noffline and online renderers, as well as recent neural rendering methods, which\ndemonstrate the superior performance of our approach for facial asset\nrendering. We also showcase diverse immersive applications of facial assets\nusing our TransGS approach and GauFace representation, across various platforms\nlike PCs, phones and even VR headsets.","PeriodicalId":501174,"journal":{"name":"arXiv - CS - Graphics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Instant Facial Gaussians Translator for Relightable and Interactable Facial Rendering\",\"authors\":\"Dafei Qin, Hongyang Lin, Qixuan Zhang, Kaichun Qiao, Longwen Zhang, Zijun Zhao, Jun Saito, Jingyi Yu, Lan Xu, Taku Komura\",\"doi\":\"arxiv-2409.07441\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose GauFace, a novel Gaussian Splatting representation, tailored for\\nefficient animation and rendering of physically-based facial assets. Leveraging\\nstrong geometric priors and constrained optimization, GauFace ensures a neat\\nand structured Gaussian representation, delivering high fidelity and real-time\\nfacial interaction of 30fps@1440p on a Snapdragon 8 Gen 2 mobile platform. Then, we introduce TransGS, a diffusion transformer that instantly translates\\nphysically-based facial assets into the corresponding GauFace representations.\\nSpecifically, we adopt a patch-based pipeline to handle the vast number of\\nGaussians effectively. We also introduce a novel pixel-aligned sampling scheme\\nwith UV positional encoding to ensure the throughput and rendering quality of\\nGauFace assets generated by our TransGS. Once trained, TransGS can instantly\\ntranslate facial assets with lighting conditions to GauFace representation,\\nWith the rich conditioning modalities, it also enables editing and animation\\ncapabilities reminiscent of traditional CG pipelines. We conduct extensive evaluations and user studies, compared to traditional\\noffline and online renderers, as well as recent neural rendering methods, which\\ndemonstrate the superior performance of our approach for facial asset\\nrendering. We also showcase diverse immersive applications of facial assets\\nusing our TransGS approach and GauFace representation, across various platforms\\nlike PCs, phones and even VR headsets.\",\"PeriodicalId\":501174,\"journal\":{\"name\":\"arXiv - CS - Graphics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-11\",\"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-2409.07441\",\"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-2409.07441","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

我们提出的 GauFace 是一种新颖的高斯拼接表示法,专为基于物理的面部资产的高效动画和渲染而定制。利用强大的几何先验和约束优化,GauFace 可确保整齐且结构化的高斯表示,在骁龙 8 代 2 移动平台上实现 30fps@1440p 的高保真和实时面部交互。具体来说,我们采用基于补丁的流水线来有效处理大量高斯。我们还引入了新颖的像素对齐采样方案和 UV 位置编码,以确保 TransGS 生成的 GauFace 资产的吞吐量和渲染质量。 经过培训后,TransGS 可以立即将光照条件下的面部资产转换为 GauFace 表征,并通过丰富的调节模式,实现与传统 CG 管线类似的编辑和动画功能。我们进行了广泛的评估和用户研究,与传统的离线和在线渲染器以及最新的神经渲染方法进行了比较,证明了我们的方法在面部资产渲染方面的卓越性能。我们还展示了使用我们的 TransGS 方法和 GauFace 表征的面部资产的各种沉浸式应用,这些应用跨越了各种平台,如 PC、手机甚至 VR 头显。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Instant Facial Gaussians Translator for Relightable and Interactable Facial Rendering
We propose GauFace, a novel Gaussian Splatting representation, tailored for efficient animation and rendering of physically-based facial assets. Leveraging strong geometric priors and constrained optimization, GauFace ensures a neat and structured Gaussian representation, delivering high fidelity and real-time facial interaction of 30fps@1440p on a Snapdragon 8 Gen 2 mobile platform. Then, we introduce TransGS, a diffusion transformer that instantly translates physically-based facial assets into the corresponding GauFace representations. Specifically, we adopt a patch-based pipeline to handle the vast number of Gaussians effectively. We also introduce a novel pixel-aligned sampling scheme with UV positional encoding to ensure the throughput and rendering quality of GauFace assets generated by our TransGS. Once trained, TransGS can instantly translate facial assets with lighting conditions to GauFace representation, With the rich conditioning modalities, it also enables editing and animation capabilities reminiscent of traditional CG pipelines. We conduct extensive evaluations and user studies, compared to traditional offline and online renderers, as well as recent neural rendering methods, which demonstrate the superior performance of our approach for facial asset rendering. We also showcase diverse immersive applications of facial assets using our TransGS approach and GauFace representation, across various platforms like PCs, phones and even VR headsets.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信