Mi-Ripple: Restoring Images Degraded by Iterative AI Editing

Papers

arxiv:2609.11317

Published on Sep 10

· Submitted by

Jiayin Chen on Sep 11

· Miyang Technology (Shanghai) Co., Ltd.

Upvote

52

Authors:

Jiayin Chen ,

,

Muting Wang

Abstract

Mi-Ripple reduces digital ripple artifacts in edited images by separating lattice artifacts from texture and applying targeted spectral filtering and reference cleaning.

Generated by thinkingmachines/Inkling-Small

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.

View arXiv page View PDF Project pageGitHub 132 Add to collection

Community

cnbird

Paper author Paper submitter 12 days ago

We investigate “digital ripples” in AI-generated images, showing how resampling introduces periodic artifacts and why they can reappear after cleanup during subsequent editing.

cnbird

Paper author Paper submitter 12 days ago

Welcome to try our website https://lab.miyang.cn/ripple/

librarian-bot

11 days ago

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

• MDTD-ArtIR: Benchmarking Image Editing and Restoration Models for Art Image Restoration under Texture-Overlay Degradations (2026)

• SatEdit: Mask-Conditioned Image Editing via VLM-Guided Segment Annotation (2026)

• MagnifiQ: Patch-aware Text Guided Progressive Upscaling for High-Resolution Image Restoration (2026)

• Fractional-Order Adaptive Motion Magnification: Phase-Reliability Weighting for Noise-Constrained Video Amplification (2026)

• BG-REAL: A Public Real-Data Anchored Benchmark for Background Manipulation Detection and Localization (2026)

• GlobalForge: Towards Robust AI-Generated Image Detection (2026)

• Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation System (2026)

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on HF Mirror checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

Upvote

52

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2609.11317 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2609.11317 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2609.11317 in a Space README.md to link it from this page.

Collections including this paper 1