10 October 2017 Image-guided depth propagation for 2-D-to-3-D video conversion using superpixel matching and adaptive autoregressive model
Author Affiliations +
J. of Electronic Imaging, 26(5), 053019 (2017). doi:10.1117/1.JEI.26.5.053019
Abstract
We propose image-guided depth propagation for two-dimensional (2-D)-to-three-dimensional (3-D) video conversion using superpixel matching and the adaptive autoregressive (AR) model. We adopt key frame-based depth propagation that propagates the depth map in the key frame to nonkey frames. Moreover, we use the adaptive AR model for depth refinement to penalize depth-color inconsistency. First, we perform superpixel matching to estimate motion vectors at the superpixel level instead of block matching based on the fixed block size. Then, we conduct depth compensation based on motion vectors to generate the depth map in the nonkey frame. However, the size of two superpixels is not exactly the same due to the segment-based matching, which causes matching errors in the compensated depth map. Thus, we introduce an adaptive image-guided AR model to minimize matching errors and produce the final depth map by minimizing AR prediction errors. Finally, we employ depth-image-based rendering to generate stereoscopic views from 2-D videos and their depth maps. Experimental results demonstrate that the proposed method successfully performs depth propagation and produces high-quality depth maps for 2-D-to-3-D video conversion.
© 2017 SPIE and IS&T
Jiji Cai, Cheolkon Jung, "Image-guided depth propagation for 2-D-to-3-D video conversion using superpixel matching and adaptive autoregressive model," Journal of Electronic Imaging 26(5), 053019 (10 October 2017). http://dx.doi.org/10.1117/1.JEI.26.5.053019 Submission: Received 24 May 2017; Accepted 14 September 2017
Submission: Received 24 May 2017; Accepted 14 September 2017
JOURNAL ARTICLE
8 PAGES


SHARE
KEYWORDS
Autoregressive models

Video

Image segmentation

Motion estimation

Motion models

3D modeling

Cameras

Back to Top