Tag
Microsoft Research introduces Mirage, a latent spatial memory that stores 3D scenes as latent tokens, achieving up to 10.57x faster video generation and 55x lower memory use with state-of-the-art consistency.
This paper introduces latent spatial memory for video world models, storing 3D scene information directly in diffusion latent space to avoid costly pixel-space reconstruction. The proposed Mirage framework achieves up to 10.57x faster generation and 55x memory reduction while achieving state-of-the-art performance on WorldScore and RealEstate10K.