A Novel Intermediate View Synthesis Method Based on Disparity Estimation

A novel intermediate view synthesis method based on disparity estimation is presented in this paper. Color distance is adopted to set truncation value adaptively when Belief Propagation (BP) algorithm is used in disparity estimation. In view interpolation, the left and right part of the image are divided into three kinds using strong and weak consistency constraints separately. Then different strategy is applied according to the characteristic of each region. Experimental results show that it can synthesize virtual images with high quality.

[1]  Qunsheng Peng,et al.  Stepwise approach for view synthesis , 2007 .

[2]  An Ping,et al.  Efficient stereo disparity estimation for intermediate view synthesis , 2004, The 2004 47th Midwest Symposium on Circuits and Systems, 2004. MWSCAS '04..

[3]  Ingemar J. Cox,et al.  Teleconferencing eye contract using a virtual camera , 1993, INTERCHI Adjunct Proceedings.

[4]  William T. Freeman,et al.  On the optimality of solutions of the max-product belief-propagation algorithm in arbitrary graphs , 2001, IEEE Trans. Inf. Theory.

[5]  Sing Bing Kang,et al.  Stereo for Image-Based Rendering using Image Over-Segmentation , 2007, International Journal of Computer Vision.