arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2609.11317cs.CV

Mi-Ripple:恢复由迭代AI编辑退化的图像

Mi-Ripple: Restoring Images Degraded by Iterative AI Editing

  • Miyang Technology (Shanghai) Co., Ltd.(米扬科技(上海)有限公司)
  • Key Laboratory of System Software (Chinese Academy of Sciences)(中国科学院系统软件重点实验室)
  • Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所)
  • University of Chinese Academy of Sciences(中国科学院大学)
  • Shanghai Jiao Tong University(上海交通大学)
  • Tianjin University(天津大学)

机构由 AI 辅助整理,请以论文原文为准。

Jiayin Chen, Yicheng Xu, Muting Wang

AI总结:

Mi-Ripple通过分离周期性伪影与颗粒纹理,结合频谱陷波、结构感知平滑和清洁参考再生,在保护结构的同时有效抑制迭代AI编辑引入的数字波纹,实现低失真恢复。

AI中文摘要:

迭代参考条件图像编辑可能引入网格状和颗粒状纹理,通常称为数字波纹。我们提出Mi-Ripple,一种诊断引导的恢复工作流,在抑制这种数字波纹的同时保护图像结构。Mi-Ripple将周期性晶格伪影与内容纠缠的颗粒纹理分离,然后结合选择性频谱陷波、结构感知平滑和清洁参考再生。这种分离使得当伪影在频谱上隔离时能够进行低失真滤波,而当滤波会抹除合法细节时则进行视觉重建。在十四次仅陷波执行中,整幅图像残差标准差在CIELAB亮度单位为0.08--0.44。在一个配对再生示例中,参考清洁将输出碎片密度降低45%。Mi-Ripple将可测量的伪影减少与视觉上更清晰的生成图像联系起来,而非仅优化频谱分数。

英文摘要:

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.

↑