| title | Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution |
|---|---|
| authors | Zixin Jessie Chen, Zhuo Chen, Archer Wang, Jeff Gore, William T. Freeman, Congyue Deng, Marin Soljačić |
| date | 2026-05-25 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.26032 |
| affiliation | Massachusetts Institute of Technology |
| upvotes | 13 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution. Despite their practical differences, both can be understood as reversing information loss across scales. We introduce SKILD, a Scale-invariant K-Space Image Learning Diffusion model that unifies generation and continuous super-resolution within a single unconditional framework. Both natural images and critical physical systems exhibit scale invariance, and we leverage it to design a forward process that attenuates image content from fine to coarse scales while injecting spectrum-matched Gaussian noise, making scale an explicit coordinate of the diffusion dynamics. The same trained reverse process performs generation and continuous super-resolution by varying only the starting timestep: no task-specific architecture, no conditioning branch, no classifier-free guidance, no retraining per scale factor. Empirically, SKILD reaches FID 2.65 and Inception Score 9.63 on unconditional CIFAR-10, performs 2times--8times super-resolution on ImageNet from a single unconditional checkpoint while outperforming conditional models across perceptual metrics, and reconstructs critical Ising models whose connected four-point correlations closely track the ground truth. |
cite
@misc{chen2026everything,
title={Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution},
author={Zixin Jessie Chen and Zhuo Chen and Archer Wang and Jeff Gore and William T. Freeman and Congyue Deng and Marin Soljačić},
year={2026},
eprint={2605.26032},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.26032}
}