Hugging Face Daily Papers · · 3 min read

Roomer: Reflective Object-Grounded Model Editing and Repair for 3D Indoor Layout Synthesis

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

Roomer attributes residual violations in synthesized 3D indoor layouts to specific object instances, applies local edits to a structured layout model, and commits each repair only after deterministic re-verification.</p>\n","updatedAt":"2026-08-04T02:46:30.009Z","author":{"_id":"62ebd791fee90fca4742ead8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62ebd791fee90fca4742ead8/8-iJYS9Wk41l6JTGtJrNf.jpeg","fullname":"levon dang","name":"levondang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8458782434463501},"editors":["levondang"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/62ebd791fee90fca4742ead8/8-iJYS9Wk41l6JTGtJrNf.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.01973","authors":[{"_id":"6a7151fbec5082b9f872cd1e","name":"Lingwei Dang","hidden":false},{"_id":"6a7151fbec5082b9f872cd1f","name":"Ziyan Qiu","hidden":false},{"_id":"6a7151fbec5082b9f872cd20","name":"Jiajia Cheng","hidden":false},{"_id":"6a7151fbec5082b9f872cd21","name":"Shishuo Shang","hidden":false},{"_id":"6a7151fbec5082b9f872cd22","name":"Zhenhao Zhang","hidden":false},{"_id":"6a7151fbec5082b9f872cd23","name":"Yufei Zhu","hidden":false},{"_id":"6a7151fbec5082b9f872cd24","name":"Qingxin Xiao","hidden":false},{"_id":"6a7151fbec5082b9f872cd25","name":"Pan Liu","hidden":false},{"_id":"6a7151fbec5082b9f872cd26","name":"Shenghui Huang","hidden":false},{"_id":"6a7151fbec5082b9f872cd27","name":"Yun Hao","hidden":false},{"_id":"6a7151fbec5082b9f872cd28","name":"Juntong Li","hidden":false},{"_id":"6a7151fbec5082b9f872cd29","name":"Qingyao Wu","hidden":false}],"publishedAt":"2026-08-03T00:00:00.000Z","submittedOnDailyAt":"2026-08-04T00:00:00.000Z","title":"Roomer: Reflective Object-Grounded Model Editing and Repair for 3D Indoor Layout Synthesis","submittedOnDailyBy":{"_id":"62ebd791fee90fca4742ead8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62ebd791fee90fca4742ead8/8-iJYS9Wk41l6JTGtJrNf.jpeg","isPro":false,"fullname":"levon dang","user":"levondang","type":"user","name":"levondang"},"summary":"Existing indoor layout generators produce globally plausible layouts yet may retain local violations such as collisions, out-of-bounds placements, obstructed openings, and blocked circulation. Most prior work focuses on full-scene synthesis or scene-level optimization, with limited support for identifying responsible objects and locally repairing affected regions. We present Roomer, a reflective repair framework that casts these violations as sparse, object-grounded repair problems. Roomer encodes layouts as ``RoState'' and uses ``RoReview'' to bind measured violations to implicated objects. A geometry-conditioned vision-language model planner proposes a structured local edit, while a deterministic solver validates it and generates a finite set of candidate edits when needed. Each candidate is committed only if full-scene verification confirms that it resolves the target violation without new hard violations or broken protected constraints. We train the planner on Roomer-CC, a controlled-corruption dataset that pairs faulty layouts with object-grounded violation evidence and known-feasible inverse StatePatches. Since existing benchmarks rarely assess whether physically valid layouts are usable, we introduce Roomer-Eval to assess distributional quality, physical validity, and practical usability. Experiments show that Roomer repairs residual violations while preserving valid regions, improves physical validity and usability, and transfers across external generators.","upvotes":8,"discussionId":"6a7151fbec5082b9f872cd2a","organization":{"_id":"65d9f8e26b8ab39009e13ba2","name":"cn-scut","fullname":"South China University of Technology","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/636608e78b6bd0d9f663f4cd/8oSX1nc7RpNDTBApOTzWL.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"62ebd791fee90fca4742ead8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62ebd791fee90fca4742ead8/8-iJYS9Wk41l6JTGtJrNf.jpeg","isPro":false,"fullname":"levon dang","user":"levondang","type":"user"},{"_id":"67a474fb3dd995045efb9f3a","avatarUrl":"/avatars/e9fbac5491fdef7b64647ef206f0ce2f.svg","isPro":false,"fullname":"y","user":"ssshang6178096","type":"user"},{"_id":"6571ce9bf469a5d950cbe83e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6571ce9bf469a5d950cbe83e/e4HhzII-e2KqVnl9gvn3x.jpeg","isPro":false,"fullname":"PPL","user":"RichL","type":"user"},{"_id":"67283f5e198c50df99c407bc","avatarUrl":"/avatars/eda5bcaa421d3c05fcae1df83176d66c.svg","isPro":false,"fullname":"jtl","user":"qlzjftm","type":"user"},{"_id":"68eb5e532c5fcae039badaf3","avatarUrl":"/avatars/d9eac0a8a87e4cf05fe3e848def193da.svg","isPro":false,"fullname":"丘梓彦","user":"qzy32","type":"user"},{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","isPro":true,"fullname":"taesiri","user":"taesiri","type":"user"},{"_id":"69d369318f9db8cdf1626a66","avatarUrl":"/avatars/598824d5708fb5e1e9e53cc2647b7b19.svg","isPro":false,"fullname":"cjj","user":"cjj135246","type":"user"},{"_id":"698964d5004a03e09ff904ee","avatarUrl":"/avatars/99fe8735207ad7204183aca915267f2f.svg","isPro":false,"fullname":"ding","user":"zongjian2","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"65d9f8e26b8ab39009e13ba2","name":"cn-scut","fullname":"South China University of Technology","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/636608e78b6bd0d9f663f4cd/8oSX1nc7RpNDTBApOTzWL.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.01973.md","query":{}}">
Papers
arxiv:2608.01973

Roomer: Reflective Object-Grounded Model Editing and Repair for 3D Indoor Layout Synthesis

Published on Aug 3
· Submitted by
levon dang
on Aug 4
Authors:
,

Abstract

Existing indoor layout generators produce globally plausible layouts yet may retain local violations such as collisions, out-of-bounds placements, obstructed openings, and blocked circulation. Most prior work focuses on full-scene synthesis or scene-level optimization, with limited support for identifying responsible objects and locally repairing affected regions. We present Roomer, a reflective repair framework that casts these violations as sparse, object-grounded repair problems. Roomer encodes layouts as ``RoState'' and uses ``RoReview'' to bind measured violations to implicated objects. A geometry-conditioned vision-language model planner proposes a structured local edit, while a deterministic solver validates it and generates a finite set of candidate edits when needed. Each candidate is committed only if full-scene verification confirms that it resolves the target violation without new hard violations or broken protected constraints. We train the planner on Roomer-CC, a controlled-corruption dataset that pairs faulty layouts with object-grounded violation evidence and known-feasible inverse StatePatches. Since existing benchmarks rarely assess whether physically valid layouts are usable, we introduce Roomer-Eval to assess distributional quality, physical validity, and practical usability. Experiments show that Roomer repairs residual violations while preserving valid regions, improves physical validity and usability, and transfers across external generators.

Community

Paper submitter about 5 hours ago

Roomer attributes residual violations in synthesized 3D indoor layouts to specific object instances, applies local edits to a structured layout model, and commits each repair only after deterministic re-verification.

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

Get this paper in your agent:

hf papers read 2608.01973
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper

No model linking this paper

Cite arxiv.org/abs/2608.01973 in a model README.md to link it from this page.

Datasets citing this paper

No dataset linking this paper

Cite arxiv.org/abs/2608.01973 in a dataset README.md to link it from this page.

Spaces citing this paper

No Space linking this paper

Cite arxiv.org/abs/2608.01973 in a Space README.md to link it from this page.

Collections including this paper

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Hugging Face Daily Papers