Title: | Improving Depth Maps by Nonlinear Diffusion |
Authors: | Yin, Jianfeng Cooperstock, Jeremy R. |
Citation: | WSCG '2004: Short Communications: the 12-th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision 2004, 2.-6. February 2004 Plzeň, p. 305-311. |
Issue Date: | 2004 |
Publisher: | Václav Skala - UNION Agency |
Document type: | konferenční příspěvek conferenceObject |
URI: | http://wscg.zcu.cz/WSCG2004/Papers_2004_Short/N83.pdf http://hdl.handle.net/11025/6571 |
ISBN: | 80-903100-5-2 |
Keywords: | hloubkové mapy;korespondenční problém;nelineární difúze;3D rekonstrukce |
Keywords in different language: | depth maps;stereo matching;nonlinear diffusion;3D reconstruction |
Abstract: | Dense depth maps, typically produced by stereo algorithms, are essential for various computer vision applications. For general configurations in which the cameras are not necessarily parallel or close together, it often proves difficult to obtain reasonable results for complex scenes, in particular in occluded or textureless regions. To improve the depth map in such regions, we propose a post-processing method and illustrate its benefits to applications such as 3D reconstruction or foreground segmentation of a user in a scene. |
Rights: | © Václav Skala - UNION Agency |
Appears in Collections: | WSCG '2004: Short Communications |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/6571
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.