標題: A DEPTH REFINEMENT ALGORITHM FOR MULTI-VIEW VIDEO SYNTHESIS
作者: Shih, Hsin-Chia
Hsiao, Hsu-Feng
資訊工程學系
Department of Computer Science
關鍵字: FTV;multi-view;depth estimation;view synthesis
公開日期: 2010
摘要: With the recent progress of display, capture device, and coding technologies, multi-view video applications such as stereoscopic video, free viewpoint TV (FTV), and free viewpoint video (FVV) have been introduced to the world with growing interest. To achieve free navigation of such applications, depth information is required along with the video data. There have been many research activities in the area of depth estimation; however, it still poses us great challenge to estimate accurate depth map. In this paper, we propose a depth refinement algorithm for multi-view video synthesis. The proposed algorithm classifies the pixel-wise depth map into two categories, one is reliable and the other is unreliable, followed by the depth refinement algorithm for those pixels with unreliable depth values. Except for the depth refinement algorithm, we also propose a reliable weighted view interpolation algorithm. At last, the refined depth map is evaluated by the quality of the synthesized view.
URI: http://hdl.handle.net/11536/26087
http://dx.doi.org/10.1109/ICASSP.2010.5495023
ISBN: 978-1-4244-4296-6
ISSN: 1520-6149
DOI: 10.1109/ICASSP.2010.5495023
期刊: 2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING
起始頁: 742
結束頁: 745
Appears in Collections:Conferences Paper


Files in This Item:

  1. 000287096000176.pdf