Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911719025016832 |
|---|---|
| author | Bang, Junseo Lee, Joonhee Lee, Kyeonghyun Lee, Haechang Kang, Dong Un Chun, Se Young |
| author_facet | Bang, Junseo Lee, Joonhee Lee, Kyeonghyun Lee, Haechang Kang, Dong Un Chun, Se Young |
| contents | Arbitrary-scale image super-resolution aims to upsample images to any desired resolution, offering greater flexibility than traditional fixed-scale super-resolution. Recent approaches based on regression-based or generative models have shown promising results but often suffer from scale inconsistency due to their single-stage formulation, which must handle a wide range of scaling factors simultaneously. To address this, we propose CasArbi, a self-cascaded diffusion framework for arbitrary-scale image super-resolution. CasArbi decomposes varying scaling factors into smaller sequential steps, progressively enhancing the image resolution at each step with seamless transitions for arbitrary scales. CasArbi leverages a coordinate-conditioned diffusion model for learning continuous image representations and adopts self-consistency guidance to generate scale-consistent details at inference time. Extensive experiments show that CasArbi outperforms existing methods in both perceptual and distortion metrics and demonstrates superior scale consistency across diverse arbitrary-scale super-resolution benchmarks. Our code is available at https://github.com/junseo88/CasArbi. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_07813 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution Bang, Junseo Lee, Joonhee Lee, Kyeonghyun Lee, Haechang Kang, Dong Un Chun, Se Young Computer Vision and Pattern Recognition Artificial Intelligence Arbitrary-scale image super-resolution aims to upsample images to any desired resolution, offering greater flexibility than traditional fixed-scale super-resolution. Recent approaches based on regression-based or generative models have shown promising results but often suffer from scale inconsistency due to their single-stage formulation, which must handle a wide range of scaling factors simultaneously. To address this, we propose CasArbi, a self-cascaded diffusion framework for arbitrary-scale image super-resolution. CasArbi decomposes varying scaling factors into smaller sequential steps, progressively enhancing the image resolution at each step with seamless transitions for arbitrary scales. CasArbi leverages a coordinate-conditioned diffusion model for learning continuous image representations and adopts self-consistency guidance to generate scale-consistent details at inference time. Extensive experiments show that CasArbi outperforms existing methods in both perceptual and distortion metrics and demonstrates superior scale consistency across diverse arbitrary-scale super-resolution benchmarks. Our code is available at https://github.com/junseo88/CasArbi. |
| title | Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2506.07813 |