Frequency-based Environment Matting by Compressive Sensing

IEEE International Conference on Computer Vision (ICCV), 2015

Yiming Qian1, Minglun Gong2, Yee-Hong Yang1
1University of Alberta, 2Memorial University of Newfoundland


Extracting environment mattes using existing approaches often requires either thousands of captured images or a long processing time, or both. In this paper, we propose a novel approach to capturing and extracting the matte of a real scene effectively and efficiently. Grown out of the traditional frequency-based signal analysis, our approach can accurately locate contributing sources. By exploiting the recently developed compressive sensing theory, we simplify the data acquisition process of frequency-based environment matting. Incorporating phase information in a frequency signal into data acquisition further accelerates the matte extraction procedure. Compared with the state-of-the-art method, our approach achieves superior performance on both synthetic and real data, while consuming only a fraction of the processing time.

    PDF (9.8 MB)   Poster   Supplementary (65 MB)

   NSERC (Natural Sciences and Engineering Research Council of Canada)
   University of Alberta