Gait as biometrics has been widely used for human identi cation. However, direction changes cause di culties for most of the gait recognition systems, due to appearance changes. This study presents an e cient multi-view gait recognition method that allows curved trajectories on completely unconstrained paths for in- door environments. Our method is based on volumet- ric reconstructions of humans, aligned along their way. A new gait descriptor, termed as Gait Entropy Vol- ume (GEnV), is also proposed. GEnV focuses on cap- turing 3D dynamical information of walking humans through the concept of entropy. Our approach does not require the sequence to be split into gait cycles. A GEnV based signature is computed on the basis of the previous 3D gait volumes. Each signature is clas- si ed by a Support Vector Machine, and a majority voting policy is used to smooth and reinforce the clas- si cations results. The proposed approach is experimen- tally validated on the \AVA Multi-View Gait Dataset (AVAMVG)" and on the \Kyushu University 4D Gait Database (KY4D)". The results show that this new ap- proach achieves promising results in the problem of gait recognition on unconstrained paths.