Abstract
The perception of an object from a single image is hard for machines but is much easier for humans as humans often have prior knowledge about the underlying nature of the object. Combining the power of human perception with the computation capability of machines has led to some key advances for ill-posed problems such as 3D reconstruction from single image. In this work we present D-sweep, a novel method for modeling 3D objects using 2D shape snapping and 3D sweep. The user assists recognition and reconstruction by choosing or drawing specific 2D shapes and placing them on either end of the object in the image. The machine first snaps the shape to the end of the object by fitting its projection to the automatically detected contour lines. Once the profile is determined, the user can sweep it along a specific 3D trajectory to reconstruct the 3D object.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Requicha, A.: Representations for rigid solids: Theory, methods, and systems. ACM Computing Surveys 12(4) (1980)
Foley, J.D., Van Dam, A., Feiner, S.K., Hughes, J.F., Phillips, R.: Introduction to Computer Graphics. Addison-Wesley (1993)
Requicha, A., Voelcker, H.: Solid modeling: a historical summary and contemporary assessment. Computer Graphics and Applications 2(2), 9–24 (1982)
Angelidis, A.: Swirling-sweepers: Constant-volume modeling. In: Proceedings of the 12th Pacific Conference on Computer Graphics and Applications, pp. 10–15 (2004)
Schmidt, R., Wyvill, B.: Generalized sweep templates for implicit modeling. In: Proceedings of the 3rd International Conference on Computer Graphics and Interactive Techniques in Australasia and South East Asia, pp. 187–196 (2005)
Debevec, P., Taylor, C., Malik, J.: Modeling and rendering architecture from photographs: A hybrid geometry-and image-based approach. In: Proceedings of ACM SIGGRAPH, pp. 11–20 (1996)
Sinha, S., Steedly, D., Szeliski, R.: Interactive 3D architectural modeling from unordered photo collections. ACM Transactions on Graphics (TOG) 27(159) (2008)
Van Den Hengel, A., Dick, A.: VideoTrace: rapid interactive scene modelling from video. ACM Transactions on Graphics (TOG) 26(3) (2007)
Gingold, Y., Igarashi, T., Zorin, D.: Structured annotations for 2D-to-3D modeling. ACM Transactions on Graphics (TOG) 28(148) (2009)
Lau, M., Saul, G., Mitani, J., Igarashi, T.: Modeling-in-context: User design of complementary objects with a single photo. In: Proceedings of the Seventh Eurographics Workshop on Sketch-Based Interfaces and Modeling, pp. 17–24 (2010)
Xu, K., Zheng, H., Zhang, H., Cohen-Or, D., Liu, L., Xiong, Y.: Photo-inspired model-driven 3D object modeling. ACM Transactions on Graphics (TOG) 30(80), 1–10 (2011)
Rother, D., Sapiro, G.: 3D Reconstruction from a Single Image. Submitted to IEEE Transactions on Pattern Analysis and Machine Learning, IMA Prepr International (2009)
Chen, T., Zhu, Z., Shamir, A., Hu, S., Cohen-Or, D.: 3-Sweep: Extracting Editable Objects from a Single Photo. ACM Transactions on Graphics (TOG) 32(195) (2013)
Igarashi, T., Matsuoka, S., Tanaka, H.: Teddy: A sketching interface for 3D freeform design. In: Proceedings of ACM SIGGRAPH, pp. 409–416 (1999)
Olsen, L., Samavati, F.F., Sousa, M.C., Jorge, J.A.: Sketch-based modeling: A survey. Computers Graphics 33(1), 85–103 (2009)
Shtof, A., Agathos, A., Gingold, Y., Shamir, A., Cohen-or, D.: Geosemantic snapping for sketch-based modeling. Computer Graphics Forum 32(2.2), 245–253 (2013)
Arbelaez, P., Maire, M.: Contour detection and hierarchical image segmentation. Pattern Analysis and Machine Learning 33(5), 898–916 (2011)
Cheng, M.: Curve structure extraction for cartoon images. In: Proceedings of the 5th Joint Conference on Harmonious Human Machine Environment, pp. 13–25 (2009)
Nocedal, J., Wright, S.J.: Numerical Optimization. Springer (2006)
Liu, D., Nocedal, J.: On the limited memory BFGS method for large scale optimization. Mathematical Programming 45, 503–528 (1989)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Hu, P., Cai, H., Bu, F. (2014). D-Sweep: Using Profile Snapping for 3D Object Extraction from Single Image. In: Christie, M., Li, TY. (eds) Smart Graphics. SG 2014. Lecture Notes in Computer Science, vol 8698. Springer, Cham. https://doi.org/10.1007/978-3-319-11650-1_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-11650-1_4
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11649-5
Online ISBN: 978-3-319-11650-1
eBook Packages: Computer ScienceComputer Science (R0)