StreamV2V: Real-time Video-to-Video Translation with User Prompts

This paper introduces StreamV2V, a diffusion model that achieves real-time streaming video-to-video translation with user prompts.

Data and Resources

Cite this as

Feng Liang, Masayoshi Tomizuka, Akio Kodaira, Kurt Keutzer, Chenfeng Xu, Diana Marculescu (2024). Dataset: StreamV2V: Real-time Video-to-Video Translation with User Prompts. https://doi.org/10.57702/jcihpc7s

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2405.15757
Author Feng Liang
More Authors
Masayoshi Tomizuka
Akio Kodaira
Kurt Keutzer
Chenfeng Xu
Diana Marculescu
Homepage https://jeff-liangf.github.io/projects/streamv2v