Matten: Video Generation with Mamba-Attention

arXiv:2405.03025v1 Announce Type: new
Abstract: In this paper, we introduce Matten, a cutting-edge latent diffusion model with Mamba-Attention architecture for video generation. With minimal computational cost, Matten employs spatial-temporal attention for local video content modeling and bidirectional Mamba for global video content modeling. Our comprehensive experimental evaluation demonstrates that Matten has competitive performance with the current Transformer-based and GAN-based models in benchmark performance, achieving superior FVD scores and efficiency. Additionally, we observe a direct positive correlation between the complexity of …

abstract architecture arxiv attention computational cost cs.cv diffusion diffusion model edge evaluation experimental global mamba modeling paper performance spatial temporal type video video generation