Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
skip to main content
10.1145/2338676.2338686acmconferencesArticle/Chapter ViewAbstractPublication PagessapConference Proceedingsconference-collections
research-article

Playing with Puffball: simple scale-invariant inflation for use in vision and graphics

Published: 03 August 2012 Publication History

Abstract

We describe how inflation, the act of mapping a 2D silhouette to a 3D region, can be applied in two disparate problems to offer insight and improvement: silhouette part segmentation and image-based material transfer. To demonstrate this, we introduce Puffball, a novel inflation technique, which achieves similar results to existing inflation approaches -- including smoothness, robustness, and scale and shift-invariance -- through an exceedingly simple and accessible formulation. The part segmentation algorithm avoids many of the pitfalls of previous approaches by finding part boundaries on a canonical 3-D shape rather than in the contour of the 2-D shape; the algorithm gives reliable and intuitive boundaries, even in cases where traditional approaches based on the 2D Minima Rule are misled. To demonstrate its effectiveness, we present data in which subjects prefer Puffball's segmentations to more traditional Minima Rule-based segmentations across several categories of silhouettes. The texture transfer algorithm utilizes Puffball's estimated shape information to produce visually pleasing and realistically synthesized surface textures with no explicit knowledge of either underlying shape.

References

[1]
Alexe, A., Gaildrat, V., and Barthe, L. 2004. Interactive modelling from sketches using spherical implicit functions. In International Conference on Computer Graphics, Virtual Reality, Visualisation and Interaction in Africa.
[2]
Blum, H. 1967. A transformation for extracting new descriptors of shape. In Models for the Perception of Speech and Visual Form, W. Whaten-Dunn, Ed. MIT Press, 362--380.
[3]
Braunstein, M., Hoffman, D. D., and Saidpour, A. 1989. Parts of visual objects: An experimental test of the minima rule. Perception 18, 16, 817--826.
[4]
DeWinter, J., and Wagemans, J. 2006. Segmentation of object outlines into parts: A large-scale integrative study. Cognition 99, 3, 275--325.
[5]
Efros, A. A., and Freeman, W. T. 2001. Image quilting for texture synthesis and transfer. In International Conference on Computer Graphics and Interactive Techniques, 341--346.
[6]
Feldman, J., and Singh, M. 2006. Bayesian estimation of the shape skeleton. Proceedings of the National Academy of Sciences 103, 47, 18014--18019.
[7]
Froyen, V., Feldman, J., and Singh, M. 2010. A bayesian framework for figure-ground interpretation. In Advances in Neural Information Processing Systems, vol. 23, 631--639.
[8]
Hoffman, D. D., and Richards, W. 1987. Parts of recognition. In Readings in computer vision: issues, problems, principles and paradigms.
[9]
Igarishi, T., Matsuoka, S., and Tanaka, H. 1999. Teddy: a sketching interface for 3d freeform design. In International Conference on Computer Graphics and Interactive Techniques: ACM SIGGRAPH Courses.
[10]
Karpenko, O. A., and Hughes, J. F. 2006. Smoothsketch: 3d free-form shapes from complex sketches. ACM Transactions on Graphics 25, 3, 589--598.
[11]
Karpenko, O., Hughes, J. F., and Raskar, R. 2002. Free-form sketching with variational implicit surfaces. Computer Graphics Forum 21, 3, 585--594.
[12]
Lefebvre, S., and Hoppe, H. 2005. Parallel controllable texture synthesis. ACM Transactions on Graphics 24, 3, 777--786.
[13]
Oswald, M. R., Toppe, E., Kolev, K., and Cremers, D. 2009. Non-parametric single view reconstruction of curved objects using convex optimization. In Proceedings of the 31st DAGM Symposium on Pattern Recognition, 171--180.
[14]
Pentland, A. P. 1990. Automatic extraction of deformable part models. International Journal of Computer Vision 4, 2, 107--126.
[15]
Prasad, M., Zisserman, A., and Fitzgibbon, A. 2006. Single-view reconstruction of curved surfaces. In Proceedings of 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1345--1354.
[16]
Siddiqi, K., and Kimia, B. B. 1995. Parts of visual form: Computational aspects. IEEE Transactions on Pattern Analysis and Machine Analysis 17, 3, 239--251.
[17]
Siddiqi, K., Tresness, K. J., and Kimi, B. B. 1996. Parts of visual form: Pyschophysical aspects. Perception 25, 4, 399--424.
[18]
Singh, M., Seyranian, G. D., and Hoffman, D. D. 1999. Parsing silhouettes: the shorcut rule. Perception and Psychophysics 61, 4, 636--660.
[19]
Tai, C.-L., Zhang, H., and Fong, C.-K. 2004. Prototype modeling from sketched silhouettes based on convolution surfaces. Computer Graphics Forum 23, 1, 71--83.
[20]
Terzopoulos, D., Witkin, A., and Kass, M. 1987. Symmetry-seeking models and 3d object recognition. International Journal of Computer Vision 1, 3, 211--221.
[21]
Terzopoulus, D., and Witkin, A. 1988. Physically based models with rigid and deformable components. IEEE Computer Graphics and Applications 8, 6, 41--51.
[22]
Tse, P. U. 2002. A contour propogation approach to surface filling-in and volume formation. Psychological Review 109, 1, 91--115.
[23]
Zhang, L., Dugas-Phocion, G., Samson, J.-S., and Seitz, S. M. 2002. Single-view modeling of free-form scenes. The Journal of Visualization and Computer Animation 13, 4, 225--235.

Cited By

View all
  • (2023)What does the Occluding Contour Tell us about Quantitative Shape?2023 20th Conference on Robots and Vision (CRV)10.1109/CRV60082.2023.00015(55-62)Online publication date: Jun-2023
  • (2019)An Approximate Shading Model with Detail Decomposition for Object RelightingInternational Journal of Computer Vision10.1007/s11263-018-1090-6127:1(22-37)Online publication date: 1-Jan-2019
  • (2017)Learning Category-Specific Deformable 3D Models for Object ReconstructionIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2016.257471339:4(719-731)Online publication date: 1-Apr-2017
  • Show More Cited By
  1. Playing with Puffball: simple scale-invariant inflation for use in vision and graphics

        Recommendations

        Comments

        Information & Contributors

        Information

        Published In

        cover image ACM Conferences
        SAP '12: Proceedings of the ACM Symposium on Applied Perception
        August 2012
        131 pages
        ISBN:9781450314312
        DOI:10.1145/2338676
        Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

        Sponsors

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        Published: 03 August 2012

        Permissions

        Request permissions for this article.

        Check for updates

        Author Tags

        1. lighting
        2. object recognition
        3. shading
        4. texture
        5. textures

        Qualifiers

        • Research-article

        Conference

        SAP '12
        Sponsor:
        SAP '12: ACM Symposium on Applied Perception 2012
        August 3 - 4, 2012
        California, Los Angeles

        Acceptance Rates

        SAP '12 Paper Acceptance Rate 21 of 40 submissions, 53%;
        Overall Acceptance Rate 43 of 94 submissions, 46%

        Contributors

        Other Metrics

        Bibliometrics & Citations

        Bibliometrics

        Article Metrics

        • Downloads (Last 12 months)2
        • Downloads (Last 6 weeks)0
        Reflects downloads up to 16 Feb 2025

        Other Metrics

        Citations

        Cited By

        View all
        • (2023)What does the Occluding Contour Tell us about Quantitative Shape?2023 20th Conference on Robots and Vision (CRV)10.1109/CRV60082.2023.00015(55-62)Online publication date: Jun-2023
        • (2019)An Approximate Shading Model with Detail Decomposition for Object RelightingInternational Journal of Computer Vision10.1007/s11263-018-1090-6127:1(22-37)Online publication date: 1-Jan-2019
        • (2017)Learning Category-Specific Deformable 3D Models for Object ReconstructionIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2016.257471339:4(719-731)Online publication date: 1-Apr-2017
        • (2017)A new modeling approach for relief and emboss2017 25th Signal Processing and Communications Applications Conference (SIU)10.1109/SIU.2017.7960661(1-4)Online publication date: May-2017
        • (2017)Learning Category-Specific 3D Shape Models from Weakly Labeled 2D Images2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)10.1109/CVPR.2017.382(3587-3595)Online publication date: Jul-2017
        • (2016)Unsupervised categorical shape reconstruction through manifolds2016 IEEE Winter Conference on Applications of Computer Vision (WACV)10.1109/WACV.2016.7477628(1-8)Online publication date: Mar-2016
        • (2016)Lifting Object Detection Datasets into 3DIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2015.243570738:7(1342-1355)Online publication date: 1-Jul-2016
        • (2016)Visual perception of shape altered by inferred causal historyScientific Reports10.1038/srep362456:1Online publication date: 8-Nov-2016
        • (2016)Bent out of shape: The visual inference of non-rigid shape transformations applied to objectsVision Research10.1016/j.visres.2015.08.009126(330-346)Online publication date: Sep-2016
        • (2015)Category-specific object reconstruction from a single image2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)10.1109/CVPR.2015.7298807(1966-1974)Online publication date: Jun-2015
        • Show More Cited By

        View Options

        Login options

        View options

        PDF

        View or Download as a PDF file.

        PDF

        eReader

        View online with eReader.

        eReader

        Figures

        Tables

        Media

        Share

        Share

        Share this Publication link

        Share on social media