2DGH:二维高斯-赫米特拼接技术实现高质量渲染和更好的几何重构

Ruihan Yu, Tianyu Huang, Jingwang Ling, Feng Xu
{"title":"2DGH:二维高斯-赫米特拼接技术实现高质量渲染和更好的几何重构","authors":"Ruihan Yu, Tianyu Huang, Jingwang Ling, Feng Xu","doi":"arxiv-2408.16982","DOIUrl":null,"url":null,"abstract":"2D Gaussian Splatting has recently emerged as a significant method in 3D\nreconstruction, enabling novel view synthesis and geometry reconstruction\nsimultaneously. While the well-known Gaussian kernel is broadly used, its lack\nof anisotropy and deformation ability leads to dim and vague edges at object\nsilhouettes, limiting the reconstruction quality of current Gaussian splatting\nmethods. To enhance the representation power, we draw inspiration from quantum\nphysics and propose to use the Gaussian-Hermite kernel as the new primitive in\nGaussian splatting. The new kernel takes a unified mathematical form and\nextends the Gaussian function, which serves as the zero-rank term in the\nupdated formulation. Our experiments demonstrate the extraordinary performance\nof Gaussian-Hermite kernel in both geometry reconstruction and novel-view\nsynthesis tasks. The proposed kernel outperforms traditional Gaussian Splatting\nkernels, showcasing its potential for high-quality 3D reconstruction and\nrendering.","PeriodicalId":501174,"journal":{"name":"arXiv - CS - Graphics","volume":"181 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"2DGH: 2D Gaussian-Hermite Splatting for High-quality Rendering and Better Geometry Reconstruction\",\"authors\":\"Ruihan Yu, Tianyu Huang, Jingwang Ling, Feng Xu\",\"doi\":\"arxiv-2408.16982\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"2D Gaussian Splatting has recently emerged as a significant method in 3D\\nreconstruction, enabling novel view synthesis and geometry reconstruction\\nsimultaneously. While the well-known Gaussian kernel is broadly used, its lack\\nof anisotropy and deformation ability leads to dim and vague edges at object\\nsilhouettes, limiting the reconstruction quality of current Gaussian splatting\\nmethods. To enhance the representation power, we draw inspiration from quantum\\nphysics and propose to use the Gaussian-Hermite kernel as the new primitive in\\nGaussian splatting. The new kernel takes a unified mathematical form and\\nextends the Gaussian function, which serves as the zero-rank term in the\\nupdated formulation. Our experiments demonstrate the extraordinary performance\\nof Gaussian-Hermite kernel in both geometry reconstruction and novel-view\\nsynthesis tasks. The proposed kernel outperforms traditional Gaussian Splatting\\nkernels, showcasing its potential for high-quality 3D reconstruction and\\nrendering.\",\"PeriodicalId\":501174,\"journal\":{\"name\":\"arXiv - CS - Graphics\",\"volume\":\"181 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-30\",\"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-2408.16982\",\"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-2408.16982","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

近来,二维高斯拼接法成为三维重建的重要方法,可同时进行新颖的视图合成和几何重建。虽然众所周知的高斯核被广泛使用,但它缺乏各向异性和变形能力,导致物体轮廓边缘模糊不清,限制了当前高斯拼接方法的重建质量。为了增强表示能力,我们从量子物理学中汲取灵感,提出使用高斯-赫米特核作为高斯拼接的新基元。新核采用统一的数学形式,并扩展了高斯函数,在更新的公式中作为零秩项。我们的实验证明了高斯-赫米特核在几何重建和新视图合成任务中的非凡性能。所提出的内核优于传统的高斯拼接内核,展示了其在高质量三维重建和渲染方面的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
2DGH: 2D Gaussian-Hermite Splatting for High-quality Rendering and Better Geometry Reconstruction
2D Gaussian Splatting has recently emerged as a significant method in 3D reconstruction, enabling novel view synthesis and geometry reconstruction simultaneously. While the well-known Gaussian kernel is broadly used, its lack of anisotropy and deformation ability leads to dim and vague edges at object silhouettes, limiting the reconstruction quality of current Gaussian splatting methods. To enhance the representation power, we draw inspiration from quantum physics and propose to use the Gaussian-Hermite kernel as the new primitive in Gaussian splatting. The new kernel takes a unified mathematical form and extends the Gaussian function, which serves as the zero-rank term in the updated formulation. Our experiments demonstrate the extraordinary performance of Gaussian-Hermite kernel in both geometry reconstruction and novel-view synthesis tasks. The proposed kernel outperforms traditional Gaussian Splatting kernels, showcasing its potential for high-quality 3D reconstruction and rendering.
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
期刊最新文献
GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representations A Missing Data Imputation GAN for Character Sprite Generation Visualizing Temporal Topic Embeddings with a Compass Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models Phys3DGS: Physically-based 3D Gaussian Splatting for Inverse Rendering
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1