Efficient Burst Super-Resolution with One-step Diffusion
This work addresses the need for efficient and high-quality burst super-resolution in image processing, though it appears incremental as it builds on existing diffusion models with efficiency improvements.
The paper tackles the problem of blurry super-resolution (SR) images from deterministic burst SR methods by using a diffusion model to reconstruct sharp and high-fidelity SR images, achieving a runtime reduction to 1.6% of the baseline while maintaining SR quality.
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.