| Stepwise approach for view synthesis |
| |
| 作者姓名： | CHAI Deng-feng PENG Qun-sheng |
| |
| 作者单位： | [1]State Key Lab of CAD and CG, Zhejiang University, Hangzhou 310027, China [2]Institute of Spatial Information Technique, Zhejiang University, Hangzhou 310027, China |
| |
| 基金项目： | Project （No. 2002CB312101） supported by the National Basic Re-search Program （973） of China |
| |
| 摘 要： | This paper presents some techniques for synthesizing novel view for a virtual viewpoint from two given views captured at different viewpoints to achieve both high quality and high efficiency. The whole process consists of three passes. The first pass recovers depth map. We formulate it as pixel labelling and propose a bisection approach to solve it. It is accomplished in log2n（n is the number of depth levels） steps,each of which involves a single graph cut computation. The second pass detects occluded pixels and reasons about their depth. It fits a foreground depth curve and a background depth curve using depth of nearby foreground and background pixels,and then distinguishes foreground and background pixels by minimizing a global energy,which involves only one graph cut computation. The third pass finds for each pixel in the novel view the corresponding pixels in the input views and computes its color. The whole process involves only a small number of graph cut computations,therefore it is efficient. And,visual artifacts in the synthesized view can be removed successfully by correcting depth of the occluded pixels. Experimental results demonstrate that both high quality and high efficiency are achieved by the proposed techniques.
|
| 关 键 词： | CAD 计算机辅助设计 曲线图 逐步法 |
| 收稿时间： | 31 December 2006 |
| 修稿时间： | 2006-08-312007-05-08 |
Stepwise approach for view synthesis |
| |
| CHAI Deng-feng PENG Qun-sheng.Stepwise approach for view synthesis[J].Journal of Zhejiang University Science,2007,8(8):1218-1226. |
| |
| Authors: | Deng-feng Chai Qun-sheng Peng |
| |
| Institution: | (1) State Key Lab of CAD and CG, Zhejiang University, Hangzhou, 310027, China;(2) Institute of Spatial Information Technique, Zhejiang University, Hangzhou, 310027, China |
| |
| Abstract: | This paper presents some techniques for synthesizing novel view for a virtual viewpoint from two given views captured at different
viewpoints to achieve both high quality and high efficiency. The whole process consists of three passes. The first pass recovers
depth map. We formulate it as pixel labelling and propose a bisection approach to solve it. It is accomplished in log2
n (n is the number of depth levels) steps, each of which involves a single graph cut computation. The second pass detects occluded
pixels and reasons about their depth. It fits a foreground depth curve and a background depth curve using depth of nearby
foreground and background pixels, and then distinguishes foreground and background pixels by minimizing a global energy, which
involves only one graph cut computation. The third pass finds for each pixel in the novel view the corresponding pixels in
the input views and computes its color. The whole process involves only a small number of graph cut computations, therefore
it is efficient. And, visual artifacts in the synthesized view can be removed successfully by correcting depth of the occluded
pixels. Experimental results demonstrate that both high quality and high efficiency are achieved by the proposed techniques.
Project (No. 2002CB312101) supported by the National Basic Research Program (973) of China |
| |
| Keywords: | View synthesis Occlusion Graph cut |
| 本文献已被 维普 SpringerLink 等数据库收录！ |
