Matten: Video Generation with Mamba-Attention

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gao, Yu, Huang, Jiancheng, Sun, Xiaopeng, Jie, Zequn, Zhong, Yujie, Ma, Lin
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914789835407360
author Gao, Yu
Huang, Jiancheng
Sun, Xiaopeng
Jie, Zequn
Zhong, Yujie
Ma, Lin
author_facet Gao, Yu
Huang, Jiancheng
Sun, Xiaopeng
Jie, Zequn
Zhong, Yujie
Ma, Lin
contents 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 our designed model and the improvement in video quality, indicating the excellent scalability of Matten.
format Preprint
id arxiv_https___arxiv_org_abs_2405_03025
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Matten: Video Generation with Mamba-Attention
Gao, Yu
Huang, Jiancheng
Sun, Xiaopeng
Jie, Zequn
Zhong, Yujie
Ma, Lin
Computer Vision and Pattern Recognition
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 our designed model and the improvement in video quality, indicating the excellent scalability of Matten.
title Matten: Video Generation with Mamba-Attention
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.03025