In sensory systems, a range of computational rules are presumed to be implemented by neuronal subpopulations with di erent tuning functions. For instance, in primate cortical area MT, di erent classes of direction-selective cells have been identi ed and related either to motion integration, segmentation or transparency. Still, how such di erent tuning properties are constructed is unclear. The dominant theoretical viewpoint based on a linear-nonlinear feed-forward cascade does not account for their complex temporal dynamics and their versatility when facing di erent input statistics. Here, we demonstrate that a recurrent network model of visual motion processing can reconcile these di erent properties. Using a ring network, we show how excitatory and inhibitory interactions can implement di erent computational rules such as vector averaging, winner-take-all or superposition. The model also captures ordered temporal transitions between these behaviors. In particular, depending on the inhibition regime the network can switch from motion integration to segmentation, thus being able to compute either a single pattern motion or to superpose multiple inputs as in motion transparency. We thus demonstrate that recurrent architectures can adaptively give rise to di erent cortical computational regimes depending upon the input statistics, from sensory ow integration to segmentation.