Separation of left and right lungs from binary segmentation is often necessary for quantitative image-based pulmonary disease evaluation. In this article, we present a new fully automated approach for accurate, robust, and efficient lung separation using 3-D CT scans. Our method follows a hysteresis setting that utilizes information from both lung regions and background gaps. First, original segmentation is separated by subtracting the gaps between left and right lungs, which are enhanced with Hessian filtering. Second, the 2-D separation manifold in 3-D image space is estimated based on the distance information from the two subsets. Finally, the separation manifold is projected back to the original segmentation in order to produce the separated lungs through optimization for addressing minor local variations. An evaluation on over 400 human and 100 small animal 3-D CT images with various abnormalities is performed. The proposed scheme successfully separated all connections on the candidate CT images. Using hysteresis mechanism, each phase is performed robustly and 3-D information is utilized to achieve a generic, efficient, and accurate solution.