iModel: interactive co-segmentation for object of interest 3d modeling
作者： Adarsh Kowdle , Dhruv Batra , Wen-Chao Chen , Tsuhan Chen
DOI: 10.1007/978-3-642-35740-4_17
关键词:
摘要: We present an interactive system to create 3D models of objects interest in their natural cluttered environments. A typical setting for modeling object involves capturing images from multiple views a multi-camera studio with mono-color screen or structured lighting. This is tedious process and cannot be applied variety objects. Moreover, general scene reconstruction algorithms fail focus on the user. In this paper, we use successful ideas cut-out literature, develop interactive-cosegmentation-based algorithm that uses scribbles user indicating foreground (object modeled) background (clutter) extract silhouettes views. Using these silhouettes, camera parameters obtained structure-from-motion, conjunction shape-from-silhouette generate texture-mapped model interest.
springer.com
sci-hub.st 参考文章(44)
Andrew W. Fitzgibbon, Geoff Cross, Andrew Zisserman, Automatic 3D Model Construction for Turn-Table Sequences european workshop on 3d structure from multiple images of large scale environments. pp. 155- 170 ,(1998) , 10.1007/3-540-49437-5_11
3D Structure from Multiple Images of Large-Scale Environments Springer Berlin Heidelberg. ,(1998) , 10.1007/3-540-49437-5
Mario Sormann, Christopher Zach, Joachim Bauer, Konrad Karner, Horst Bischof, Automatic foreground propagation in image sequences for 3D reconstruction dagm conference on pattern recognition. pp. 93- 100 ,(2005) , 10.1007/11550518_12
Keith Forbes, Fred Nicolls, Gerhard de Jager, Anthon Voigt, Shape-from-Silhouette with two mirrors and an uncalibrated camera european conference on computer vision. pp. 165- 178 ,(2006) , 10.1007/11744047_13
Dhruv Batra, Adarsh Kowdle, Devi Parikh, Jiebo Luo, Tsuhan Chen, iCoseg: Interactive co-segmentation with intelligent scribble guidance computer vision and pattern recognition. pp. 3169- 3176 ,(2010) , 10.1109/CVPR.2010.5540080
Marc Levoy, Jeremy Ginsberg, Jonathan Shade, Duane Fulk, Kari Pulli, Brian Curless, Szymon Rusinkiewicz, David Koller, Lucas Pereira, Matt Ginzton, Sean Anderson, James Davis, The digital Michelangelo project: 3D scanning of large statues international conference on computer graphics and interactive techniques. pp. 131- 144 ,(2000) , 10.1145/344779.344849
Yasutaka Furukawa, Brian Curless, Steven M. Seitz, Richard Szeliski, Towards Internet-scale multi-view stereo computer vision and pattern recognition. pp. 1434- 1441 ,(2010) , 10.1109/CVPR.2010.5539802
Brian Curless, Marc Levoy, A volumetric method for building complex models from range images international conference on computer graphics and interactive techniques. pp. 303- 312 ,(1996) , 10.1145/237170.237269
Ricardo Fabbri, Benjamin Kimia, 3D curve sketch: Flexible curve-based stereo reconstruction and calibration computer vision and pattern recognition. pp. 1538- 1545 ,(2010) , 10.1109/CVPR.2010.5539787
J.-S. Franco, E. Boyer, Exact Polyhedral Visual Hulls british machine vision conference. ,vol. 1, pp. 1- 10 ,(2003) , 10.5244/C.17.32