Challenges and advances in interactive modeling

Many important computer graphics applications rely on 3D models of real-world scenes. The current approach for modeling such scenes is first to acquire depth and color data and then to build a model off line. The approach is slow, the acquisition devices are expensive, and the resulting models are incomplete and of uneven quality. We propose an interactive modeling strategy where an operator scans the scene with a handheld device and the model is built incrementally. The evolving model is displayed continually for immediate feedback. The advantages of the interactive modeling approach are short modeling times, good scene coverage, even sampling, and low cost. Implementing the interactive modeling pipeline poses the following challenges: devising an acquisition device that is lightweight, compact and robust, real-time depth extraction, real-time registration, and real-time incremental modeling. In this paper, we analyze these advantages and challenges in light of our experience in designing an interactive modeling system.

[1]  Marc Levoy,et al.  Light field rendering , 1996, SIGGRAPH.

[2]  W.R. Scott,et al.  View planning with a registration constraint , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[3]  Luc Van Gool,et al.  Real-time range scanning of deformable surfaces by adaptively coded structured light , 2003, Fourth International Conference on 3-D Digital Imaging and Modeling, 2003. 3DIM 2003. Proceedings..

[4]  Marc Levoy,et al.  Real-time 3D model acquisition , 2002, ACM Trans. Graph..

[5]  Shenchang Eric Chen,et al.  QuickTime VR: an image-based approach to virtual environment navigation , 1995, SIGGRAPH.

[6]  PeronaPietro,et al.  3D Photography Using Shadows in Dual-Space Geometry , 1999 .

[7]  Leonard McMillan,et al.  Plenoptic Modeling: An Image-Based Rendering System , 2023 .

[8]  Patrick Hébert A self-referenced hand-held range sensor , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[9]  Giancarlo Ferrigno,et al.  Autoscan: A Flexible and Portable 3D Scanner , 1998, IEEE Computer Graphics and Applications.

[10]  Ruzena Bajcsy,et al.  Occlusions as a Guide for Planning the Next View , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Svetha Venkatesh,et al.  Low-cost interactive active monocular range finder , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[12]  Voicu Popescu,et al.  The ModelCamera: a hand-held device for interactive modeling , 2003, Fourth International Conference on 3-D Digital Imaging and Modeling, 2003. 3DIM 2003. Proceedings..

[13]  Richard Szeliski,et al.  The lumigraph , 1996, SIGGRAPH.