We present a new data structure for encoding the appearance of a ge-ometric model as seen from a viewing region (view cell). This representation can be used in interactive or real-time visualization applications to replace a complex model by an impostor, maintaining high quality rendering while cutting down rendering time. Our approach relies on an object-space sampled representation similar to a point cloud or a layered depth image, but introduces two fundamental additions to previous techniques. First, the sampling rate is controlled to pro-vide sufficient density across all possible viewing conditions from the specified view cell. Second, a correct, antialiased representation of the plenoptic function is computed using Monte Carlo integration. Our system therefore achieves high quality rendering using a simple representation with bounded complexity. We demonstrate the method for an application in urban visualization.