Texture Size Reduction Through Symmetric Overlap and Texture Carving

IF 7.8 1区 计算机科学 Q1 COMPUTER SCIENCE, SOFTWARE ENGINEERING ACM Transactions on Graphics Pub Date : 2025-01-25 DOI:10.1145/3714408
Julian Knodt, Xifeng Gao
{"title":"Texture Size Reduction Through Symmetric Overlap and Texture Carving","authors":"Julian Knodt, Xifeng Gao","doi":"10.1145/3714408","DOIUrl":null,"url":null,"abstract":"Maintaining memory efficient 3D assets is critical for game development due to size constraints for applications, and runtime costs such as GPU data transfers. While most prior work on 3D modeling focuses on reducing triangle count, few works focus on reducing texture sizes. We propose an automatic approach to reduce the texture size for 3D models while maintaining the rendered appearance of the original input. The two core components of our approach are: (1) <jats:italic>Overlapping</jats:italic> identical UV charts and <jats:italic>folding</jats:italic> mirrored regions within charts through an optimal transport optimization, and (2) <jats:italic>Carving</jats:italic> redundant and void texels in a UV-aware and texture-aware way without inverting the UV mesh. The first component creates additional void space, while the second removes void space, and their combination can greatly increase texels utilized by the UV mesh at lower texture resolutions. Our method is robust and general, and can process a 3D model with arbitrary UV layout and multiple textures without modifying the 3D mesh. We evaluate our approach on 110 models from the Google Scanned Object dataset and 64 models from Sketchfab. Compared to other approaches, ours has on average 1-3 dB PSNR higher rendering similarity and reduces pixelation in visual comparisons.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"58 1","pages":""},"PeriodicalIF":7.8000,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Transactions on Graphics","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1145/3714408","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 0

Abstract

Maintaining memory efficient 3D assets is critical for game development due to size constraints for applications, and runtime costs such as GPU data transfers. While most prior work on 3D modeling focuses on reducing triangle count, few works focus on reducing texture sizes. We propose an automatic approach to reduce the texture size for 3D models while maintaining the rendered appearance of the original input. The two core components of our approach are: (1) Overlapping identical UV charts and folding mirrored regions within charts through an optimal transport optimization, and (2) Carving redundant and void texels in a UV-aware and texture-aware way without inverting the UV mesh. The first component creates additional void space, while the second removes void space, and their combination can greatly increase texels utilized by the UV mesh at lower texture resolutions. Our method is robust and general, and can process a 3D model with arbitrary UV layout and multiple textures without modifying the 3D mesh. We evaluate our approach on 110 models from the Google Scanned Object dataset and 64 models from Sketchfab. Compared to other approaches, ours has on average 1-3 dB PSNR higher rendering similarity and reduces pixelation in visual comparisons.
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
由于应用程序的大小限制以及 GPU 数据传输等运行时成本,保持高效内存的 3D 资产对游戏开发至关重要。之前有关三维建模的大部分工作都集中在减少三角形数量上,但很少有工作集中在减少纹理大小上。我们提出了一种自动方法来减少三维模型的纹理大小,同时保持原始输入的渲染外观。我们方法的两个核心部分是(1) 重叠相同的 UV 图表,并通过最佳传输优化折叠图表中的镜像区域;以及 (2) 在不反转 UV 网格的情况下,以 UV 感知和纹理感知的方式雕刻冗余和空洞纹理。第一种方法可以创建额外的空白空间,第二种方法可以去除空白空间,两者结合可以大大提高 UV 网格在较低纹理分辨率下的像素利用率。我们的方法既稳健又通用,可以处理具有任意 UV 布局和多种纹理的三维模型,而无需修改三维网格。我们在谷歌扫描对象数据集的 110 个模型和 Sketchfab 的 64 个模型上评估了我们的方法。与其他方法相比,我们的方法在渲染相似度方面平均高出 1-3 dB PSNR,并在视觉对比中减少了像素化现象。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
ACM Transactions on Graphics
ACM Transactions on Graphics 工程技术-计算机:软件工程
CiteScore
14.30
自引率
25.80%
发文量
193
审稿时长
12 months
期刊介绍: ACM Transactions on Graphics (TOG) is a peer-reviewed scientific journal that aims to disseminate the latest findings of note in the field of computer graphics. It has been published since 1982 by the Association for Computing Machinery. Starting in 2003, all papers accepted for presentation at the annual SIGGRAPH conference are printed in a special summer issue of the journal.
期刊最新文献
Encoded Marker Clusters for Auto-Labeling in Optical Motion Capture Direct Rendering of Intrinsic Triangulations Texture Size Reduction Through Symmetric Overlap and Texture Carving Don't Splat your Gaussians: Volumetric Ray-Traced Primitives for Modeling and Rendering Scattering and Emissive Media Implicit Bonded Discrete Element Method with Manifold Optimization
×
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