AI Paper Atlas

Research map / 3D vision / 3D generation

Taming LLMs for Codematic Indoor Scene Generation

yixun liang, Qianyi Wu, Chuan Fang, Rui Chen, Jiahang Liu, Jianfeng Zhang, Ping Tan

ECCV 2026 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add CMI training recipe (ablation)Qwen3-4B-Instruct finetune · Component ablationInstruction Following: 6.371 -> 6.988Improved
add CMI training recipe (ablation)Qwen3-4B-Instruct finetune · Component ablationLayout Fidelity & Completeness: 6.557 -> 6.806Improved
add planning phase on top of CMI recipe (ablation)SceneSpinner · Component ablationInstruction Following: 6.988 -> 7.631Improved
add planning phase on top of CMI recipe (ablation)SceneSpinner · Component ablationLayout Fidelity & Completeness: 6.806 -> 7.157Improved
add both planning phase and CMI recipe (ablation)Qwen3-4B-Instruct finetune · Component ablationInstruction Following: 6.371 -> 7.631Improved
use SceneSpinner instead of HoloDeckHoloDeck · Codematic scene generationInstruction Following: 5.722 -> 7.852Improved
use SceneSpinner instead of HoloDeckHoloDeck · Codematic scene generationLayout Fidelity & Completeness: 6.037 -> 7.191Improved
use SceneSpinner instead of HoloDeckHoloDeck · Codematic scene generationCLIP Score: 0.259 -> 0.260No clear effect
add planning stage (ablation)SceneSpinner · attention analysis (bunk bed prompt)attention on instructionImproved
train without CMI regulation (ablation)SceneSpinner · training analysisKL divergence / instruction followingHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy