Efficient Burst Super-Resolution with One-step Diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kawai, Kento, Oba, Takeru, Tokoro, Kyotaro, Akita, Kazutoshi, Ukita, Norimichi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909694742757376
author Kawai, Kento
Oba, Takeru
Tokoro, Kyotaro
Akita, Kazutoshi
Ukita, Norimichi
author_facet Kawai, Kento
Oba, Takeru
Tokoro, Kyotaro
Akita, Kazutoshi
Ukita, Norimichi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_13607
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Burst Super-Resolution with One-step Diffusion
Kawai, Kento
Oba, Takeru
Tokoro, Kyotaro
Akita, Kazutoshi
Ukita, Norimichi
Computer Vision and Pattern Recognition
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.
title Efficient Burst Super-Resolution with One-step Diffusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.13607