<html><head><style type='text/css'>p { margin: 0; }</style></head><body><div style='font-family: arial,helvetica,sans-serif; font-size: 10pt; color: #000000'>Fisher Yu will present his research seminar/general exam on Tuesday May 14 at 2PM in <br>Room 402. The members of his committee are: Tom Funkhouser (advisor), Szymon <br>Rusinkiewicz, and Adam Finkelstein. Everyone is invited to attend his talk and those <br>faculty wishing to remain for the oral exam following are welcome to do so. His abstract<br>and reading list follow below.<br>---------------------<div style="color:#000;font-weight:normal;font-style:normal;text-decoration:none;font-family:Helvetica,Arial,sans-serif;font-size:12pt;"><div dir="ltr"><br><div class="gmail_default" style="font-family:arial,helvetica,sans-serif"><p style="font-size:12.666666984558105px">Abstract:</p><p style="font-size:12.666666984558105px">City scale reconstruction is gaining more and more attention these years driven by its popularity in consumer market. It can help people get familiar with a new place without physically being there. Nowadays, people can view the 3D city models from aerial view or check the panorama images of the street. However, although the street level virtual scene can give the users an immersed experience in the virtual environment, the technology to build large scale detailed 3D textured models is still not mature enough for the customers. In this project, we make use of both laser range scanning and images from Google Street View project to recover the 3D shapes and their texture by combining the sparse shape information of the range scans and detailed texture information of the images. As we are working towards the goal, there are mainly three problems we need to solve, namely, adjusting pose estimation, increase the resolution of the scans, and fill the holes in the regions the scanners failed to reach. To adjust the pose estimation, we build a framework to optimize the laser and image poses together. Also, we can optimize the scan point positions and their subdivided mesh by considering both photo consistency and scan measurement. Our methods can now work on a number of sample environments.</p>
<p style="font-size:12.666666984558105px">Reading List:</p><p style="font-size:12.666666984558105px">Szeliski, R. (2010). Computer vision: Algorithms and applications.<i>Springer-Verlag New York Inc.</i></p><p style="font-size:12.666666984558105px">
Musialski, P., Wonka, P., Aliaga, D. G., Wimmer, M., Van Gool, L., & Purgathofer, W. (2012). A Survey of Urban Reconstruction.<i> Eurographics 2012 - State of the Art Reports.</i></p><p style="font-size:12.666666984558105px">
Triggs, B., McLauchlan, P. F., Hartley, R. I., & Fitzgibbon, A. W. (2000). Bundle Adjustment — A Modern Synthesis. <i>Vision Algorithms: Theory and Practice</i><br></p><p style="font-size:12.666666984558105px">Furukawa, Y., & Ponce, J. (2010). Accurate, Dense, and Robust Multiview Stereopsis. <i>Pattern Analysis and Machine Intelligence</i></p>
<p style="font-size:12.666666984558105px">Furukawa, Y., Curless, B., Seitz, S. M., & Szeliski, R. (2010). Towards Internet-scale multi-view stereo. <i>Computer Vision and Pattern Recognition</i></p><p style="font-size:12.666666984558105px">
Snavely, N., Seitz, S. M., & Szeliski, R. (2007). Modeling the World from Internet Photo Collections. <i>International Journal of Computer Vision</i></p><p style="font-size:12.666666984558105px">Kazhdan, M., & Hoppe, H. (2013). Screened Poisson Surface Reconstruction.<i>ACM Transactions on Graphics</i>.</p>
<p style="font-size:12.666666984558105px">Lowe, D. G. (2004). Distinctive Image Features from Scale-Invariant Keypoints.<i>International Journal of Computer Vision</i></p><p style="font-size:12.666666984558105px">Pollefeys, M., Nistér, D., Frahm, J., Akbarzadeh, A., Mordohai, P., Clipp, B., Engels, C., et al. (2007). Detailed Real-Time Urban 3D Reconstruction from Video. <i>International Journal of Computer Vision</i></p>
<p style="font-size:12.666666984558105px">Seitz, S. M., Curless, B., Diebel, J., Scharstein, D., & Szeliski, R. (2006). A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms.<i> Computer Vision and Pattern Recognition</i></p>
<p style="font-size:12.666666984558105px">Hernández, C., & Vogiatzis, G. (2010). Shape from photographs : a multi-view stereo pipeline. <i>Computer Vision Studies in Computational Intelligence</i></p><p style="font-size:12.666666984558105px">
Sorkine, O. (2005). Laplacian mesh processing. <i>Eurographics 2005 - State of the Art Reports</i></p></div></div><div class="gmail_extra"><br></div></div><br></div></body></html>