Parametric channel estimation in mmWave not only enables the anticipated large spectral efficiency gains of \acs{MIMO} systems but also reveals important propagation parameters, allowing for a low complexity representation of the channel matrix. In this work, we propose to use atomic norm as a gridless multidimensional spectral estimation approach to address parametric channel estimation where both AoD and AoA are identified. The conditions for recovery of the propagation parameters are given depending on properties of the measurement matrix, and on structural features such as the antenna geometry or the number of scatters to resolve. The proposed methodology is compared against several state-of-the-art parametric approaches.