Issue No. 08 - Aug. (2013 vol. 19)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TVCG.2013.14
Song-Pei Du , Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China
Shi-Min Hu , Dept. of Comput. Sci., Tsinghua Univ., Beijing, China
R. R. Martin , Sch. of Comput. Sci. & Inf., Cardiff Univ., Cardiff, UK
Traditional image editing techniques cannot be directly used to edit stereoscopic ("3D”) media, as extra constraints are needed to ensure consistent changes are made to both left and right images. Here, we consider manipulating perspective in stereoscopic pairs. A straightforward approach based on depth recovery is unsatisfactory: Instead, we use feature correspondences between stereoscopic image pairs. Given a new, user-specified perspective, we determine correspondence constraints under this perspective and optimize a 2D warp for each image that preserves straight lines and guarantees proper stereopsis relative to the new camera. Experiments verify that our method generates new stereoscopic views that correspond well to expected projections, for a wide range of specified perspective. Various advanced camera effects, such as dolly zoom and wide angle effects, can also be readily generated for stereoscopic image pairs using our method.
Stereo image processing, Cameras, Image segmentation, Humans, Image edge detection, Robustness, Visualization, warping, Stereoscopic images, stereopsis, perspective
R. R. Martin, Shi-Min Hu and Song-Pei Du, "Changing Perspective in Stereoscopic Images," in IEEE Transactions on Visualization & Computer Graphics, vol. 19, no. , pp. 1288-1297, 2013.