Efficient Burst Super-Resolution with One-Step Diffusion
Abstract
While burst Low-Resolution (LR) images are useful for improving their Super Resolution (SR) image compared to a single LR image, prior burst SR methods are trained in a deterministic manner, which produces a blurry SR image. Since such blurry images are perceptually degraded, we aim to reconstruct sharp and high-fidelity SR images by a diffusion model. Our method improves the efficiency of the diffusion model with a stochastic sampler with a high-order ODE as well as one-step diffusion using knowledge distillation. Our experimental results demonstrate that our method can reduce the runtime to 1.6 % of its baseline while maintaining the SR quality measured based on image distortion and perceptual quality.
Cite
Text
Kawai et al. "Efficient Burst Super-Resolution with One-Step Diffusion." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.Markdown
[Kawai et al. "Efficient Burst Super-Resolution with One-Step Diffusion." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.](https://mlanthology.org/cvprw/2025/kawai2025cvprw-efficient/)BibTeX
@inproceedings{kawai2025cvprw-efficient,
title = {{Efficient Burst Super-Resolution with One-Step Diffusion}},
author = {Kawai, Kento and Oba, Takeru and Tokoro, Kyotaro and Akita, Kazutoshi and Ukita, Norimichi},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2025},
pages = {864-873},
url = {https://mlanthology.org/cvprw/2025/kawai2025cvprw-efficient/}
}