Paralleled mesh refinement for surface reconstruction

One method was proposed for mesh refinement in surface reconstruction which can be considered as a critical problem to monocular reconstruction. The main idea of the method is the implementation can be applicable and efficient by parallelization. It is un-necessary to conform photo-consistent constrain, alternatively, time-consistency is introduced in by a view-dependent way. The experimental result shows that the time-consumption can be controlled on common hardware since the energy minimization algorithm can be highly paralleled implementation based on GPU-acceleration.

[1]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[2]  Michael M. Kazhdan,et al.  Poisson surface reconstruction , 2006, SGP '06.

[3]  Rüdiger Westermann,et al.  Acceleration techniques for GPU-based volume rendering , 2003, IEEE Visualization, 2003. VIS 2003..

[4]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision: Camera Geometry and Single View Geometry , 2004 .

[5]  Richard Szeliski,et al.  Building Rome in a day , 2009, ICCV.

[6]  Jean Ponce,et al.  Accurate, Dense, and Robust Multiview Stereopsis , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Andrew J. Davison,et al.  Live dense reconstruction with a single moving camera , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[9]  D. Cohen-Or,et al.  Robust moving least-squares fitting with sharp features , 2005, ACM Trans. Graph..

[10]  Takeo Kanade,et al.  Three-dimensional scene flow , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Richard Szeliski,et al.  A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[12]  Hauke Strasdat,et al.  Real-time monocular SLAM: Why filter? , 2010, 2010 IEEE International Conference on Robotics and Automation.

[13]  H. Opower.  Multiple view geometry in computer vision , 2002 .

[14]  M. Ament,et al.  Volume Rendering , 2015 .

[15]  Long Quan,et al.  A quasi-dense approach to surface reconstruction from uncalibrated images , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Tony DeRose,et al.  Surface reconstruction from unorganized points , 1992, SIGGRAPH.