Papers
arxiv:2509.24142

Asymmetric VAE for One-Step Video Super-Resolution Acceleration

Published on Sep 29
Authors:
,
,
,

Abstract

FastVSR improves inference efficiency in diffusion-based video super-resolution by using high compression VAEs, pixel shuffle, channel replication, and a lower-bound-guided training strategy.

AI-generated summary

Diffusion models have significant advantages in the field of real-world video super-resolution and have demonstrated strong performance in past research. In recent diffusion-based video super-resolution (VSR) models, the number of sampling steps has been reduced to just one, yet there remains significant room for further optimization in inference efficiency. In this paper, we propose FastVSR, which achieves substantial reductions in computational cost by implementing a high compression VAE (spatial compression ratio of 16, denoted as f16). We design the structure of the f16 VAE and introduce a stable training framework. We employ pixel shuffle and channel replication to achieve additional upsampling. Furthermore, we propose a lower-bound-guided training strategy, which introduces a simpler training objective as a lower bound for the VAE's performance. It makes the training process more stable and easier to converge. Experimental results show that FastVSR achieves speedups of 111.9 times compared to multi-step models and 3.92 times compared to existing one-step models. We will release code and models at https://github.com/JianzeLi-114/FastVSR.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2509.24142 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2509.24142 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2509.24142 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.