VALSE 首页 活动通知 好文作者面授招 查看内容

20160706-21张弛:MeshStereo: A Global Stereo Model with Mesh Alignment...

2016-7-4 11:48| 发布者: 程一-计算所| 查看: 6923| 评论: 0

摘要: 报告嘉宾:张弛(中山大学)报告时间:2016年7月6日(星期三)晚20:00(北京时间)报告题目:MeshStereo: A Global Stereo Model with Mesh Alignment Regularization for View Interpolation主持人:郭振华(清华大 ...



报告题目:MeshStereo: A Global Stereo Model with Mesh Alignment Regularization for View Interpolation

主持人:  郭振华(清华大学深圳研究生院)

报告摘要:We present a novel global stereo model designed for view interpolation. Unlike existing stereo models which only output a disparity map, our model is able to output a 3D triangular mesh, which can be directly used for view interpolation. To this aim, we partition the input stereo images into 2D triangles with shared vertices. Lifting the 2D triangulation to 3D naturally generates a corresponding mesh. A technical difficulty is to properly split vertices to multiple copies when they appear at depth discontinuous boundaries. To deal with this problem, we formulate our objective as a two-layer MRF, with the upper layer modeling the splitting properties of the vertices and the lower layer optimizing a region-based stereo matching. Experiments on the Middlebury and the Herodion datasets demonstrate that our model is able to synthesize visually coherent new view angles with high PSNR, as well as outputting high quality disparity maps which rank at the first place on the new challenging high resolution Middlebury 3.0 benchmark.

参考文献:Zhang C, Li Z, Cheng Y, et al. Meshstereo: A global stereo model with mesh alignment regularization for view interpolation[C]//Proceedings of the IEEE International Conference on Computer Vision. 2015: 2057-2065.

报告人简介:Chi Zhang is in a Joint PhD program between Sun Yat-Sen University (SYSU) and Microsoft Research Asia (MSRA) starting from September 2012, co-supervised by Prof. Hongyang Chao from SYSU and Dr. Yong Rui from Microsoft. He is working very closely with his mentor Zhiwei Li, who is currently a Lead Researcher from the MSRA Multimedia Search and Mining Group. His currently research interests are on Stereo Matching, SLAM for object scanning, and Multiview Reconstruction for Image Based Rendering. He has published several papers in top journals and conferences, including TVGG\ICCV\ECCV\CVPR.



小黑屋|手机版|Archiver|Vision And Learning SEminar

GMT+8, 2021-1-25 22:35 , Processed in 0.012753 second(s), 15 queries .

Powered by Discuz! X3.4

Copyright © 2001-2020, Tencent Cloud.