|Title:||Robust Video Stitching and Street-View Navigation|
|Date:||March 23, 2018 (Friday)|
|Time:||4:00 p.m. - 5:00 p.m.|
|Venue:||Room 121, 1/F, Ho Sin-hang Engineering Building,
The Chinese University of Hong Kong,
|Speaker:||Prof. Hanqiu Sun
VR, Visualization and Imaging Research Centre
Department of Computer Science and Engineering
The Chinese University of Hong Kong
Stitching videos captured by mobile cameras that usually contain heavy shakiness and large parallax is practical but challenging. We propose the unified optimization of video stitching and stabilization that tackles the issues simultaneously. Since stitching relies on feature matches between input videos, and there inevitably exist false matches, we propose to encapsulate the false match elimination scheme and our optimization most optimally. The computed stabilization is the best for stitching, based on which we produce better stitching results compared to previous methods. We test the stitching and stability scores to evaluate the produced panoramic videos quantitatively. Wide-baseline street-view navigation is useful but challenging. We present a lightweight and efficient approach using homography computing and refining operators between input views. We combine homography fitting and propagation based on reliable/unreliable superpixels. We integrate the concepts of homography and mesh warping, and propose a novel homography constrained warping formulation that enforces smoothness between neighboring homographies. The proposed approach improves the state of the art, and shows that homography computation suffices for street-view navigation. Our experiments on city/rural datasets validate the efficiency and effectiveness of our approach.
Prof. Sun received M.S. in electrical engineering from University of British Columbia, and Ph.D. in computer science from University of Alberta, Canada. Prof. Sun has published more than hundred technical papers refereed in VR/CG journals and international conferences, including MIT Journal of PRESENCE, Journal of Virtual Reality, IEEE Transactions on Visualization and Computer Graphics, IEEE Transactions on Image Processing, IEEE Transactions on SMC, IEEE transactions on CSVT, ACM SIGGRAPH Asia, Computational Geometry, IEEE Transactions on Information Technology, Journal of Algorithms, Journal of Visual Languages and Computing, Journal of Applied Mathematics, IEEE journal of CGA, Computers & Graphics, Computer Graphics Forum, refereed book chapters and international conferences. She has served as guest editors of MIT PRESENCE, Journal of CAVW and IJIG, program co-chair of ACM VRST, organization co-chair of Pacific Graphics, CGI, CASA, director of advanced workshop on VR. Her current research interests include virtual reality, interactive modeling/rendering, image/video synopsis, computer-assisted surgery, fluids and Haptics simulations.
Tea, coffee and cookies will be provided after seminar.
Enquiries: Ms. Crystal Tam at tel. 3943 8439
For more information, please refer to http://www.cse.cuhk.edu.hk/seminar.