User assisted disparity remapping for stereo images

作者：

Highlights：

• A user assisted stereo image segmentation/disparity remapping method is proposed using superpixel primitives as graph nodes in the MRF based energy minimization framework.

• The technique provides a tool for emphasizing/de-emphasizing an object in the scene by virtually changing the depth in the direction of the camera axis.

• The proposed technique could also be used as a post-processing step for retargeting stereoscopic footage on different display sizes and resolutions.

• Quantitative and qualitative experiments verify the proposed hypothesis.

摘要

Highlights•A user assisted stereo image segmentation/disparity remapping method is proposed using superpixel primitives as graph nodes in the MRF based energy minimization framework.•The technique provides a tool for emphasizing/de-emphasizing an object in the scene by virtually changing the depth in the direction of the camera axis.•The proposed technique could also be used as a post-processing step for retargeting stereoscopic footage on different display sizes and resolutions.•Quantitative and qualitative experiments verify the proposed hypothesis.

论文关键词：Disparity remapping,Stereo segmentation,Graph cut,User interaction,Feature matching

论文评审过程：Received 26 November 2012, Revised 2 August 2013, Accepted 3 August 2013, Available online 24 August 2013.

论文官网地址：https://doi.org/10.1016/j.image.2013.08.003