Indoor Scene Generation

Follow this topic Ask about this topic

Indoor scene generation studies how to turn descriptions, images, floor plans, and user needs into coherent room layouts and 3D environments. Methods range from procedural rules and scene graphs to diffusion models, autoregressive generators, and language-model agents that plan, validate, and refine object placement. The results can support architectural design and create interactive environments for robotics and simulation. A central challenge is balancing visual realism and semantic control with physical validity, usability, and efficient editing, especially in complex or multi-room spaces.

Latest papers

64 papers8 papers in the last four weeks, up 167% on the four weeks before. 0.0% of all new papers.

Design-MLLM: A Reinforcement Alignment Framework for Verifiable and Aesthetic Interior Design
Mar 4, 2026Yuxuan Yang, Xiaotong Mao, Jingyao WangLLM Alignment Indoor Scene Generation
Nanjing Forestry University, Nanjing, China · Université de Lorraine, Nancy, France · Laboratoire Réactions et Génie des Procédés, Nancy, France +2
RoboLayout: Differentiable 3D Scene Generation for Embodied Agents
Feb 18, 2026Ali Shamsaddinlou3D Scene Layout Generation 3D Scene Generation
SceneReVis: A Self-Reflective Vision-Grounded Framework for 3D Indoor Scene Synthesis via Multi-Turn RL
Feb 10, 2026Yang Zhao, Shizhao Sun, Meisheng Zhang +33D Scene Generation Indoor Scene Generation
Shanghai Jiao Tong University, Shanghai, China · Microsoft Research Asia, Beijing, China · Peking University, Beijing, China +1
ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing
Jun 3, 2025Martin JJ. Bucher, Iro Armeni3D Scene Editing 3D Scene Representation
Stanford University

Mar 4, 2026J/K move · Enter open · S save

Design-MLLM: A Reinforcement Alignment Framework for Verifiable and Aesthetic Interior Design

Yuxuan Yang, Xiaotong Mao, Jingyao Wang

Nanjing Forestry University, Nanjing, China · Université de Lorraine, Nancy, France · Laboratoire Réactions et Génie des Procédés, Nancy, France+2

LLM Alignment Indoor Scene Generation RL for VLMs Preference-Based RL

Open paper AskPDF arXiv

Interior design is a requirements-to-visual-plan generation process that must simultaneously satisfy verifiable spatial feasibility and comparative aesthetic preferences. While recent multimodal large language models (MLLMs) offer a unified foundation for interpreting user intent and producing design rationales, our empirical analysis reveals a persistent contradiction in real-world deployment: MLLMs often produce layouts that are unbuildable and aesthetically inconsistent. These findings indicate that simply adding in-domain text is insufficient; effective interior design requires an alignment mechanism that separates hard constraints from soft preferences and coordinates them during optimization. To address this, we propose Design-MLLM, a reinforcement alignment framework that optimizes a feasibility-first preference objective via a dual-branch, aesthetic-oriented reward. Specifically, Design-MLLM (i) explicitly evaluates spatial feasibility using programmatic constraint checks, (ii) assesses aesthetic preference only among feasible candidates to avoid visually appealing but unexecutable shortcuts, and (iii) performs group-relative optimization to obtain stable preference signals. Through this process, Design-MLLM learns a controllable policy that consistently selects and generates solutions that are both executable and aesthetically coherent, rather than occasionally producing visually appealing but infeasible designs. Extensive experiments on various benchmark datasets demonstrate the advantages of Design-MLLM.

Latest papers

Design-MLLM: A Reinforcement Alignment Framework for Verifiable and Aesthetic Interior Design

RoboLayout: Differentiable 3D Scene Generation for Embodied Agents

SceneReVis: A Self-Reflective Vision-Grounded Framework for 3D Indoor Scene Synthesis via Multi-Turn RL

ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing