Abstract: Real-time unsupervised anomaly detection from videos is challenging due to the uncertainty in occurrence and definition of abnormal events. To overcome this ambiguity, an unsupervised adversarial learning model is proposed to detect such unusual events. The proposed end-to-end system is based on a Generative Adversarial Network (GAN) architecture with spatiotemporal feature learning and a new Singular Value Decomposition (SVD) loss function for robust reconstruction and video anomaly detection. The loss employs efficient low-rank approximations of the matrices involved to drive the convergence of the model. During training, the model strives to learn the relevant normal data distribution. Anomalies are then detected as frames whose reconstruction error, based on such distribution, shows a significant deviation. The model is efficient and lightweight due to our adoption of depth-wise separable convolution. The complete system is validated upon several benchmark datasets and proven to be robust for complex video anomaly detection, in terms of both AUC and Equal Error Rate (EER).