Sketch123: Multi-spectral channel cross attention for sketch-based 3D generation via diffusion models

IF 3 3区 计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING
Zhentong Xu , Long Zeng , Junli Zhao , Baodong Wang , Zhenkuan Pan , Yong-Jin Liu
{"title":"Sketch123: Multi-spectral channel cross attention for sketch-based 3D generation via diffusion models","authors":"Zhentong Xu ,&nbsp;Long Zeng ,&nbsp;Junli Zhao ,&nbsp;Baodong Wang ,&nbsp;Zhenkuan Pan ,&nbsp;Yong-Jin Liu","doi":"10.1016/j.cad.2025.103896","DOIUrl":null,"url":null,"abstract":"<div><div>With the development of generative techniques, sketch-driven 3D reconstruction has gained substantial attention as an efficient 3D modeling technique. However, challenges remain in extracting detailed features from sketches, representing local geometric structures, and ensuring generated fidelity and stability. To address these issues, in this paper we propose a multi-spectral channel cross-attention model for sketch reconstruction, which leverages the complementary strengths of frequency and spatial domains to capture multi-level sketch features. Our method employs a two-stage diffusion generation mechanism, additionally, a Sparse Feature Enhancement Module (SFE) replaces traditional down-sampling, reducing feature loss and enhancing detail preservation and noise suppression through a Laplace voxel smoothing operator. The Wasserstein distance introduced and integrated as part of the loss function, stabilizes the generative process using optimal transport theory to support high-quality 3D model reconstruction. Extensive experiments verify that our model surpasses state-of-the-art methods in terms of generation accuracy, local control, and generalization ability, providing an efficient, precise solution for transforming sketches into 3D models.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"185 ","pages":"Article 103896"},"PeriodicalIF":3.0000,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer-Aided Design","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0010448525000582","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 0

Abstract

With the development of generative techniques, sketch-driven 3D reconstruction has gained substantial attention as an efficient 3D modeling technique. However, challenges remain in extracting detailed features from sketches, representing local geometric structures, and ensuring generated fidelity and stability. To address these issues, in this paper we propose a multi-spectral channel cross-attention model for sketch reconstruction, which leverages the complementary strengths of frequency and spatial domains to capture multi-level sketch features. Our method employs a two-stage diffusion generation mechanism, additionally, a Sparse Feature Enhancement Module (SFE) replaces traditional down-sampling, reducing feature loss and enhancing detail preservation and noise suppression through a Laplace voxel smoothing operator. The Wasserstein distance introduced and integrated as part of the loss function, stabilizes the generative process using optimal transport theory to support high-quality 3D model reconstruction. Extensive experiments verify that our model surpasses state-of-the-art methods in terms of generation accuracy, local control, and generalization ability, providing an efficient, precise solution for transforming sketches into 3D models.
Sketch123:多光谱通道交叉关注通过扩散模型生成基于草图的3D
随着生成技术的发展,草图驱动的三维重建作为一种高效的三维建模技术得到了广泛的关注。然而,在从草图中提取细节特征、表示局部几何结构以及确保生成的保真度和稳定性方面仍然存在挑战。为了解决这些问题,本文提出了一种多频谱通道交叉注意模型用于草图重建,该模型利用频率域和空间域的互补优势来捕获多层次的草图特征。我们的方法采用两阶段扩散生成机制,此外,稀疏特征增强模块(SFE)取代传统的下采样,减少特征损失,并通过拉普拉斯体素平滑算子增强细节保存和噪声抑制。Wasserstein距离作为损失函数的一部分引入并集成,使用最优传输理论稳定生成过程,以支持高质量的3D模型重建。大量的实验证明,我们的模型在生成精度,局部控制和泛化能力方面超过了最先进的方法,为将草图转换为3D模型提供了高效,精确的解决方案。
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 求助全文
来源期刊
Computer-Aided Design
Computer-Aided Design 工程技术-计算机:软件工程
CiteScore
5.50
自引率
4.70%
发文量
117
审稿时长
4.2 months
期刊介绍: Computer-Aided Design is a leading international journal that provides academia and industry with key papers on research and developments in the application of computers to design. Computer-Aided Design invites papers reporting new research, as well as novel or particularly significant applications, within a wide range of topics, spanning all stages of design process from concept creation to manufacture and beyond.
×
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