15 February 2016 Joint geodesic depth propagation for two-dimensional-to-three-dimensional video conversion
Author Affiliations +
Abstract
We propose joint geodesic depth propagation (JGDP) for two-dimensional-to-three-dimensional video conversion. To save substantial human effort and produce high-quality depth maps, we adopt a key-frame depth propagation strategy based on a geodesic distance. First, we perform block matching between current and reference frames to estimate motion vectors (MVs). Second, we conduct depth compensation from the reference depth map for obtaining the current depth map based on MVs. Finally, we refine the depth map using joint geodesic filtering. Experimental results demonstrate that JGDP achieves an average 2.4-dB gain in peak-signal-to-noise ratio and 0.019 gain in structure similarity over state-of-the-art depth propagation methods.
© 2016 SPIE and IS&T
Cheolkon Jung, Jiji Cai, "Joint geodesic depth propagation for two-dimensional-to-three-dimensional video conversion," Journal of Electronic Imaging 25(1), 013030 (15 February 2016). https://doi.org/10.1117/1.JEI.25.1.013030 . Submission:
JOURNAL ARTICLE
7 PAGES


SHARE
RELATED CONTENT

Subpixel edge detection method based on low-frequency filtering
Proceedings of SPIE (September 28 2016)
High dynamic range video with ghost removal
Proceedings of SPIE (September 07 2010)
Depth map upscaling through edge-weighted optimization
Proceedings of SPIE (January 30 2012)

Back to Top