Joint Depth and Alpha Matte Optimization via Stereo

This study presents a novel iterative algorithm of joint depth and alpha matte optimization via stereo (JDMOS). This algorithm realizes simultaneous estimation of depth map and matting image to obtain final convergence. The depth map provides depth information to realize automatic image matting, whereas the border details generated from the image matting can refine the depth map in boundary areas. Compared with monocular matting methods, another advantage offered by JDMOS is that the image matting process is completely automatic, and the result is significantly more robust when depth information is introduced. The major contribution of JDMOS is adding image matting information to the cost function, thereby refining the depth map, especially in the scene boundary. Similarly, optimized disparity information is stitched into the matting algorithm as prior knowledge to make the foreground–background segmentation more accurate. Experimental results on Middlebury datasets demonstrate the effectiveness of JDMOS.

[1]  Stefano Mattoccia,et al.  Accurate and Efficient Cost Aggregation Strategy for Stereo Correspondence Based on Approximated Joint Bilateral Filtering , 2009, ACCV.

[2]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[3]  Lu Fang,et al.  Stereo matching by adaptive weighting selection based cost aggregation , 2013, 2013 IEEE International Symposium on Circuits and Systems (ISCAS2013).

[4]  Liming Chen,et al.  A Fast Trilateral Filter-Based Adaptive Support Weight Method for Stereo Matching , 2015, IEEE Transactions on Circuits and Systems for Video Technology.

[5]  Dah-Jye Lee,et al.  Dense Disparity Real-Time Stereo Vision Algorithm for Resource-Limited Systems , 2011, IEEE Transactions on Circuits and Systems for Video Technology.

[6]  Richard Szeliski,et al.  Stereo Matching with Transparency and Matting , 1999, International Journal of Computer Vision.

[7]  Richard Szeliski,et al.  High-quality video view interpolation using a layered representation , 2004, SIGGRAPH 2004.

[8]  Y. Mukaigawa,et al.  Large Deviations Estimates for Some Non-local Equations I. Fast Decaying Kernels and Explicit Bounds , 2022 .

[9]  David Salesin,et al.  A Bayesian approach to digital matting , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[10]  Álvaro Arranz,et al.  Multiresolution energy minimisation framework for stereo matching , 2012 .

[11]  Dani Lischinski,et al.  A Closed-Form Solution to Natural Image Matting , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Richard Szeliski,et al.  A layered approach to stereo reconstruction , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[13]  Richard Szeliski,et al.  Stereo Matching with Transparency and Matting , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[14]  Haidi Ibrahim,et al.  Literature Survey on Stereo Vision Disparity Map Algorithms , 2016, J. Sensors.

[15]  René Vidal,et al.  Estimation of Alpha Mattes for Multiple Image Layers , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Michael F. Cohen,et al.  Simultaneous Matting and Compositing , 2006, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Miao Liao,et al.  Joint depth and alpha matte optimization via fusion of stereo and time-of-flight sensor , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.