摘要: We propose a new depth-based representation of 3-D scenes primarily for the problem arbitrary view synthesis. The information contained in given image sequence is compacted into single multivalued array, where points are organized by occlusions rather than coherent affine motions. This grouping facilitates an automatic process to determine number layers and helps reduce artifacts caused scene. In addition, iterative multiframe dynamic programming algorithm described produce piecewise smooth depth maps. A novel segmentation, tracking, plane fitting also proposed handle traditionally difficult low-contrast regions. Reconstructed views as well flyarounds real presented demonstrate effectiveness approach.
sci-hub.se 参考文章(9)
Avideh Zakhor, Nelson Liang An Chang, Depth-based representations of three-dimensional scenes for view synthesis University of California, Berkeley. ,(1999)
Zhengyou Zhang, Rachid Deriche, Olivier Faugeras, Quang-Tuan Luong, A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry Artificial Intelligence. ,vol. 78, pp. 87- 119 ,(1995) , 10.1016/0004-3702(95)00022-4
Shenchang Eric Chen, Lance Williams, View interpolation for image synthesis Proceedings of the 20th annual conference on Computer graphics and interactive techniques - SIGGRAPH '93. pp. 279- 288 ,(1993) , 10.1145/166117.166153
H.S. Sawhney, S. Ayer, Compact representations of videos through dominant and multiple motion estimation IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 18, pp. 814- 830 ,(1996) , 10.1109/34.531801
S. Baker, R. Szeliski, P. Anandan, A layered approach to stereo reconstruction computer vision and pattern recognition. pp. 434- 441 ,(1998) , 10.1109/CVPR.1998.698642
J.Y.A. Wang, E.H. Adelson, Representing moving images with layers IEEE Transactions on Image Processing. ,vol. 3, pp. 625- 638 ,(1994) , 10.1109/83.334981
N.L. Chang, A. Zakhor, View generation for three-dimensional scenes from video sequences IEEE Transactions on Image Processing. ,vol. 6, pp. 584- 598 ,(1997) , 10.1109/83.563323
N.L. Chang, A. Zakhor, Finite sensor effects for estimating structure-from-motion international conference on image processing. ,vol. 1, pp. 918- 922 ,(1998) , 10.1109/ICIP.1998.723669
M. Okutomi, T. Kanade, A multiple-baseline stereo IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 15, pp. 353- 363 ,(1993) , 10.1109/34.206955