Data-driven structural priors for shape completion
Tóm tắt
Acquiring 3D geometry of an object is a tedious and time-consuming task, typically requiring scanning the surface from multiple viewpoints. In this work we focus on reconstructing complete geometry from a single scan acquired with a low-quality consumer-level scanning device. Our method uses a collection of example 3D shapes to build structural part-based priors that are necessary to complete the shape. In our representation, we associate a local coordinate system to each part and learn the distribution of positions and orientations of all the other parts from the database, which implicitly also defines positions of symmetry planes and symmetry axes. At the inference stage, this knowledge enables us to analyze incomplete point clouds with substantial occlusions, because observing only a few regions is still sufficient to infer the global structure. Once the parts and the symmetries are estimated, both data sources, symmetry and database, are fused to complete the point cloud. We evaluate our technique on a synthetic dataset containing 481 shapes, and on real scans acquired with a Kinect scanner. Our method demonstrates high accuracy for the estimated part structure and detected symmetries, enabling higher quality shape completions in comparison to alternative techniques.
Từ khóa
Tài liệu tham khảo
Choi S. Zhou Q.-Y. and Koltun V. 2015. Robust reconstruction of indoor scenes. CVPR. Choi S. Zhou Q.-Y. and Koltun V. 2015. Robust reconstruction of indoor scenes. CVPR.
Felzenszwalb P. McAllester D. and Ramanan D. 2008. A discriminatively trained multiscale deformable part model. In IEEE CVPR 1--8. Felzenszwalb P. McAllester D. and Ramanan D. 2008. A discriminatively trained multiscale deformable part model. In IEEE CVPR 1--8.
Janoch , A. , Karayev , S. , Jia , Y. , Barron , J. , Fritz , M. , Saenko , K. , and Darrell , T . 2011. A category-level 3-d object dataset: Putting the kinect to work . In ICCV Workshop on Consumer Depth Cameras in Computer Vision, 1168--1174 . Janoch, A., Karayev, S., Jia, Y., Barron, J., Fritz, M., Saenko, K., and Darrell, T. 2011. A category-level 3-d object dataset: Putting the kinect to work. In ICCV Workshop on Consumer Depth Cameras in Computer Vision, 1168--1174.
Lai , K. , Bo , L. , Ren , X. , and Fox , D . 2011. A large-scale hierarchical multi-view rgb-d object dataset . In IEEE ICRA , 1817--1824. Lai, K., Bo, L., Ren, X., and Fox, D. 2011. A large-scale hierarchical multi-view rgb-d object dataset. In IEEE ICRA, 1817--1824.
Pauly M. Mitra N. J. Giesen J. Gross M. and Guibas L. 2005. Example-based 3d scan completion. SGP. Pauly M. Mitra N. J. Giesen J. Gross M. and Guibas L. 2005. Example-based 3d scan completion. SGP.
Wu C. Lenz I. and Saxena A. 2014. Hierarchical semantic labeling for task-relevant rgb-d perception. RSS. Wu C. Lenz I. and Saxena A. 2014. Hierarchical semantic labeling for task-relevant rgb-d perception. RSS.
Xie Z. Xu K. Liu L. and Xiong Y. 2014. 3d shape segmentation and labeling via extreme learning machine. SGP. Xie Z. Xu K. Liu L. and Xiong Y. 2014. 3d shape segmentation and labeling via extreme learning machine. SGP.
Xu K. Zhang H. Cohen-Or D. and Chen B. 2012. Fit and diverse: Set evolution for inspiring 3d shape galleries. 57:1--57:10. Xu K. Zhang H. Cohen-Or D. and Chen B. 2012. Fit and diverse: Set evolution for inspiring 3d shape galleries. 57:1--57:10.