Non-line-of-sight (NLOS) imaging technique aims to reconstruct the hidden objects from multi-path echoes, which is a promising application in urban environment perception and autonomous driving. In this paper, we propose a total variation (TV) regularization based sparse reconstruct method for the hidden targets 3-D imaging in the seeing around corner situation for millimeter-wave (mmW) radar. Firstly, the 3-D imaging model of NLOS mmW radar is presented. Secondly, for preserving contour information, an effective imaging algorithm with compressed sensing theory and mirror projection, dubbed mirror symmetry sparse total variation (MSSTV) is proposed for 3-D image reconstruction. Finally, the MSSTV algorithm is validated by an NLOS 3-D imaging mmW experimental system with different kinds of targets.