We investigate “digital ripples” in AI-generated images, showing how resampling introduces periodic artifacts and why they can reappear after cleanup during subsequent editing.</p>\n","updatedAt":"2026-09-11T09:09:34.627Z","author":{"_id":"69e1eb933ceb9605d4db2007","avatarUrl":"/avatars/d2899498627e36d573965d713ec87c89.svg","fullname":"Jiayin Chen","name":"cnbird","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9349417686462402},"editors":["cnbird"],"editorAvatarUrls":["/avatars/d2899498627e36d573965d713ec87c89.svg"],"reactions":[],"isReport":false}},{"id":"6aa3c89639e94c1d942333fb","author":{"_id":"69e1eb933ceb9605d4db2007","avatarUrl":"/avatars/d2899498627e36d573965d713ec87c89.svg","fullname":"Jiayin Chen","name":"cnbird","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false},"createdAt":"2026-09-11T09:23:34.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Welcome to try our website https://lab.miyang.cn/ripple/","html":"<p>Welcome to try our website <a href=\"https://lab.miyang.cn/ripple/\" rel=\"nofollow\">https://lab.miyang.cn/ripple/</a></p>\n","updatedAt":"2026-09-11T09:23:34.323Z","author":{"_id":"69e1eb933ceb9605d4db2007","avatarUrl":"/avatars/d2899498627e36d573965d713ec87c89.svg","fullname":"Jiayin Chen","name":"cnbird","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.4036255478858948},"editors":["cnbird"],"editorAvatarUrls":["/avatars/d2899498627e36d573965d713ec87c89.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2609.11317","authors":[{"_id":"6aa3967047a406da7901e7ff","user":{"_id":"69e1eb933ceb9605d4db2007","avatarUrl":"/avatars/d2899498627e36d573965d713ec87c89.svg","isPro":false,"fullname":"Jiayin Chen","user":"cnbird","type":"user","name":"cnbird"},"name":"Jiayin Chen","status":"claimed_verified","statusLastChangedAt":"2026-09-11T08:45:04.759Z","hidden":false},{"_id":"6aa3967047a406da7901e800","name":"Yicheng Xu","hidden":false},{"_id":"6aa3967047a406da7901e801","user":{"_id":"6a1ecd3fdc5908e8dd1d2fba","avatarUrl":"/avatars/c38bad66752804d41dace2df11b575d8.svg","isPro":false,"fullname":"muwing wang","user":"muwing","type":"user","name":"muwing"},"name":"Muting Wang","status":"claimed_verified","statusLastChangedAt":"2026-09-11T09:53:18.773Z","hidden":false}],"publishedAt":"2026-09-10T00:00:00.000Z","submittedOnDailyAt":"2026-09-11T00:00:00.000Z","title":"Mi-Ripple: Restoring Images Degraded by Iterative AI Editing","submittedOnDailyBy":{"_id":"69e1eb933ceb9605d4db2007","avatarUrl":"/avatars/d2899498627e36d573965d713ec87c89.svg","isPro":false,"fullname":"Jiayin Chen","user":"cnbird","type":"user","name":"cnbird"},"summary":"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.","upvotes":18,"discussionId":"6aa3967147a406da7901e802","projectPage":"https://lab.miyang.cn/ripple/","githubRepo":"https://github.com/miyang-ai/Mi-Ripple","githubRepoAddedBy":"user","ai_summary":"Mi-Ripple reduces digital ripple artifacts in edited images by separating lattice artifacts from texture and applying targeted spectral filtering and reference cleaning.","ai_keywords":["Mi-Ripple","digital ripple","periodic lattice artifacts","spectral notching","structure-aware smoothing","cleaned-reference regeneration","CIELAB lightness"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":32,"organization":{"_id":"6aa3c33df87217ec43aa3ecc","name":"Miyang-AI","fullname":"Miyang Technology (Shanghai) Co., Ltd.","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/69e1eb933ceb9605d4db2007/-cr0jWbvkbFP9qIHCwfXX.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"69e1eb933ceb9605d4db2007","avatarUrl":"/avatars/d2899498627e36d573965d713ec87c89.svg","isPro":false,"fullname":"Jiayin Chen","user":"cnbird","type":"user"},{"_id":"647d89b41a1fcad2fdbeb618","avatarUrl":"/avatars/884667c8b4a4b12390e4b8032a346f92.svg","isPro":false,"fullname":"yicheng xu","user":"itshen","type":"user"},{"_id":"63f4e6033aa49d8cb97696e9","avatarUrl":"/avatars/a75b71cb047fb6eb2d7e15ccae6d5cfc.svg","isPro":false,"fullname":"yq","user":"wyq09","type":"user"},{"_id":"64aa1d87cc73827ce68e5add","avatarUrl":"/avatars/b181743646c48ef0cb070359337ea5f4.svg","isPro":false,"fullname":"zhizhengyang","user":"pzc163","type":"user"},{"_id":"6661973bf1b37cace2ccff8d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/lpbvPQ8Y3p3xvp83voYH0.jpeg","isPro":false,"fullname":"why","user":"whhyy","type":"user"},{"_id":"6941947b5f643e5367e8c825","avatarUrl":"/avatars/d30457da6ebd59847a824051ac6e871a.svg","isPro":false,"fullname":"xiaofenggan","user":"xiaofenggan","type":"user"},{"_id":"68862be6bc432a62b441784d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/Af7g9H15tHAY6a7yxBibj.png","isPro":false,"fullname":"gaosunhao","user":"gaosunhao","type":"user"},{"_id":"6aa3c991fc8293b01a96ec5f","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/Nv7P2erbnkopcvUmiChVB.png","isPro":false,"fullname":"袁永斌","user":"yuanyongbin321","type":"user"},{"_id":"6363d9d0084f49059783bc33","avatarUrl":"/avatars/3b4c52c41b076cf57281126d4c9e7fd5.svg","isPro":false,"fullname":"HY","user":"Iceah","type":"user"},{"_id":"69eaeb40b4a46a1a4e4f7317","avatarUrl":"/avatars/46dabd27e079c2a43bdc1f733487d381.svg","isPro":false,"fullname":"Jia","user":"FransicJia","type":"user"},{"_id":"6aa3ca78b5146fc82ea3b265","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/YJH7eF6gPDadUEYTubCNc.jpeg","isPro":false,"fullname":"sailoun","user":"sailoun","type":"user"},{"_id":"681ac815a58f84090660b940","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/NuEh9Gv0-o55WqvWNCZbh.png","isPro":false,"fullname":"XiHong Wu","user":"sion97","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"6aa3c33df87217ec43aa3ecc","name":"Miyang-AI","fullname":"Miyang Technology (Shanghai) Co., Ltd.","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/69e1eb933ceb9605d4db2007/-cr0jWbvkbFP9qIHCwfXX.png"},"query":{}}">

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

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

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

Add this paper to a collection to link it from this page.