| title | Mi-Ripple: Restoring Images Degraded by Iterative AI Editing |
|---|---|
| authors | Jiayin Chen, Yicheng Xu, Muting Wang |
| date | 2026-09-10 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.11317 |
| affiliation | Miyang Technology (Shanghai) Co., Ltd. |
| upvotes | 29 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Iterative reference-conditioned image editing can introduce grid-like and granular textures, commonly described as digital ripple. We present Mi-Ripple, a diagnosis-guided restoration workflow that suppresses this digital ripple while protecting image structure. Mi-Ripple separates periodic lattice artifacts from content-entangled granular texture, then combines selective spectral notching, structure-aware smoothing, and cleaned-reference regeneration. This separation enables low-distortion filtering when artifacts are spectrally isolated and visual reconstruction when filtering would erase legitimate detail. Across fourteen notch-only executions, whole-image residual standard deviation is 0.08--0.44 in CIELAB lightness units. In a paired regeneration example, reference cleaning reduces output debris density by 45\%. Mi-Ripple links measurable artifact reduction to visibly cleaner generated images, rather than optimizing a spectral score alone. |
cite
@misc{chen2026mi,
title={Mi-Ripple: Restoring Images Degraded by Iterative AI Editing},
author={Jiayin Chen and Yicheng Xu and Muting Wang},
year={2026},
eprint={2609.11317},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.11317}
}