arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.12702cs.CVcs.AI
收藏

TransCAD:用于从点云推断CAD序列的层次化Transformer

TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Clouds

University of Luxembourg(卢森堡大学);Artec 3D(Artec 3D公司);SnT(SnT研究院)

Elona Dupont, Kseniya Cherenkova, Dimitrios Mallis, Gleb Gusev, Anis Kacem, Djamila Aouada

AI总结:

TransCAD提出一种层次化Transformer架构,从点云端到端预测CAD序列,引入循环精化器回归草图参数,在DeepCAD和Fusion360上取得最先进结果,并新提出CAD序列平均精度均值度量。

摘要:

三维逆向工程,即根据物理对象的三维扫描推断CAD模型,是一个具有许多有前景的实际应用的研究方向。本文提出了TransCAD,一种端到端的基于Transformer的架构,用于从点云预测CAD序列。TransCAD通过使用层次化学习策略来利用CAD序列的结构。还引入了一个循环精化器来回归草图基元参数。在DeepCAD和Fusion360数据集上的严格实验表明,TransCAD取得了最先进的结果。结果分析得到了为CAD序列提出的度量标准——CAD序列的平均精度均值——的支持,该度量解决了现有度量的局限性。

英文摘要:

3D reverse engineering, in which a CAD model is inferred given a 3D scan of a physical object, is a research direction that offers many promising practical applications. This paper proposes TransCAD, an end-to-end transformer-based architecture that predicts the CAD sequence from a point cloud. TransCAD leverages the structure of CAD sequences by using a hierarchical learning strategy. A loop refiner is also introduced to regress sketch primitive parameters. Rigorous experimentation on the DeepCAD and Fusion360 datasets show that TransCAD achieves state-of-the-art results. The result analysis is supported with a proposed metric for CAD sequence, the mean Average Precision of CAD Sequence, that addresses the limitations of existing metrics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑