Isometric conversion of mechanical sketches into 3d models

被引：0

作者：

Tanaka M. ^{[1
]}

Asano T. ^{[2
]}

Higashino C. ^{[2
]}

机构：

[1] Okayamaity University of Science, Japan

[2] Aikoku Alpha Corporation, Japan

来源：

Computer-Aided Design and Applications | 2020年 / 18卷 / 04期

关键词：

3D Model; Human Perception; Isometric; SFBCM; Sketch; Sketch Feature;

D O I：

10.14733/cadaps.2021.772-785

中图分类号：

学科分类号：

摘要：

Sketches in the form of line drawings are important illustrations to directly express the overviews of objects, especially mechanical objects. Numerous methods that automatically convert sketches into 3D models have been proposed. However, no practical system for conversion has been developed till now. Consequently, we developed a method for this conversion. In our SFBCM (Sketch Feature-Based Conversion Method), when a sketch is input, sketch features that indicate simple sketches of objects such as cubes, cylinders are detected and extracted as 3D features step by step. Consequently, a 3D model can be obtained by combining them based on the sketch. However, the implementation of SFBCM has remained an important issue. In this paper, an algorithm for the implementation of SFBCM is proposed. For a simpler implementation, this algorithm applies human perception. For example, people prefer to draw isometric and symmetric sketches of objects. Consequently, various types of sketches can be handled in this algorithm. The effectiveness of revised SFBCM with this algorithm is demonstrated with three complex examples, and the limitations and issues are discussed in detail. © 2020 CAD Solutions, LLC.

引用

页码：772 / 785

页数：13

共 28 条

[1]

Bobenrieth C., Cordier F., Habibi A., Seo H., Descriptive: Interactive 3D Shape Modeling from A Single Descriptive Sketch, Computer-Aided Design, 128, 102904

[2]

Chen Q., Nguyen V., Han F., Kiveris R., Tu Z., Topology-Aware Single-Image 3D Shape Reconstruction, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 270-271, (2020)

[3]

Choy C, Xu D., Gwak J., Chen K., Savarese S., 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction, Computer Vision – ECCV, pp. 628-644, (2016)

[4]

Clowes M.B., On seeing things, Artificial Intelligence, 2, 1, pp. 79-116, (1971)

[5]

Company P., Piquer A., Contero M., Naya F., A survey on geometrical reconstruction as a core technology to sketch-based modeling, Computers & Graphics, 29, 6, pp. 892-904, (2005)

[6]

Company P., Ashley P., Varley C., A method for reconstructing sketched polyhedral shapes with rounds and fillets, Smart Graphics, Lecture Notes in Computer Science, 6133, pp. 152-155, (2010)

[7]

Company P., Plumed R., Varley P. A. C., Camba J. D., Algorithmic Perception of Vertices in Sketched Drawings of Polyhedral Shapes, ACM Transactions on Applied Perception, 16, 3, (2019)

[8]

Grimstead I. J., Martin R. R., Creating solid models from single 2D sketches, Proceedings of the third ACM symposium on SMA ’95, pp. 323-337, (1995)

[9]

Guo T., Cui R., Qin X., Wang Y., Tang Z., Bottom-up/top-down geometric object reconstruction with CNN classification for mobile education, PG '18: Proceedings of the 26th Pacific Conference on Computer Graphics and Applications, pp. 13-16, (2018)

[10]

Hall P., Owen M., Simple canonical views, Proc. BMVC, pp. 839-848, (2005)

← 1 2 3 →