{"ID":2892932,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.13607","arxiv_id":"2507.13607","title":"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.","short_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-fideli...","url_abs":"https://arxiv.org/abs/2507.13607","url_pdf":"https://arxiv.org/pdf/2507.13607v1","authors":"[\"Kento Kawai\",\"Takeru Oba\",\"Kyotaro Tokoro\",\"Kazutoshi Akita\",\"Norimichi Ukita\"]","published":"2025-07-18T02:21:29Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}