Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution
This addresses the flexibility problem in image upscaling for computer vision applications, representing an incremental improvement over existing diffusion-based approaches.
The paper tackles arbitrary-scale image super-resolution by proposing CasArbi, a self-cascaded diffusion framework that breaks scaling into sequential steps, outperforming prior methods on perceptual and distortion metrics across benchmarks.
Arbitrary-scale image super-resolution aims to upsample images to any desired resolution, offering greater flexibility than traditional fixed-scale super-resolution. Recent approaches in this domain utilize regression-based or generative models, but many of them are a single-stage upsampling process, which may be challenging to learn across a wide, continuous distribution of scaling factors. Progressive upsampling strategies have shown promise in mitigating this issue, yet their integration with diffusion models for flexible upscaling remains underexplored. Here, we present CasArbi, a novel self-cascaded diffusion framework for arbitrary-scale image super-resolution. CasArbi meets the varying scaling demands by breaking them down into smaller sequential factors and progressively enhancing the image resolution at each step with seamless transitions for arbitrary scales. Our novel coordinate-guided residual diffusion model allows for the learning of continuous image representations while enabling efficient diffusion sampling. Extensive experiments demonstrate that our CasArbi outperforms prior arts in both perceptual and distortion performance metrics across diverse arbitrary-scale super-resolution benchmarks.