SfmCAD: Unsupervised CAD Reconstruction by Learning Sketch-based Feature Modeling Operations | |
Li, Pu1,2; Guo, Jianwei1,2; Li, Huibin2; Benes, Bedrich3; Yan, Dong-Ming1,2 | |
2024-08-22 | |
会议日期 | 2024-6-17至2024-6-24 |
会议地点 | Seattle, USA |
英文摘要 | This paper introduces SfmCAD, a novel unsupervised network that reconstructs 3D shapes by learning the Sketch-based Feature Modeling operations commonly used in modern CAD workflows. Given a 3D shape represented as voxels, SfmCAD learns a neural-typed sketch+path parameterized representation, including 2D sketches of feature primitives and their 3D sweeping paths without supervision, for inferring feature-based CAD programs. SfmCAD employs 2D sketches for local detail representation and 3D paths to capture the overall structure, achieving a clear separation between shape details and structure. This conversion into parametric forms enables users to seamlessly adjust the shape's geometric and structural features, thus enhancing interpretability and user control. We demonstrate the effectiveness of our method by applying SfmCAD to many different types of objects, such as CAD parts, ShapeNet objects, and tree shapes. Extensive comparisons show that SfmCAD produces compact and faithful 3D reconstructions with superior quality compared to alternatives. The code is released at https://github.com/BunnySoCrazy/SfmCAD |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/57143] ![]() |
专题 | 模式识别国家重点实验室_三维可视计算 |
通讯作者 | Guo, Jianwei |
作者单位 | 1.MAIS, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Purdue University |
推荐引用方式 GB/T 7714 | Li, Pu,Guo, Jianwei,Li, Huibin,et al. SfmCAD: Unsupervised CAD Reconstruction by Learning Sketch-based Feature Modeling Operations[C]. 见:. Seattle, USA. 2024-6-17至2024-6-24. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论