SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution
Summary
SceneMosaic combines learned image priors with vision-language agents to efficiently generate diverse, physically valid indoor scenes, achieving a 24x speedup and improved physical validity over existing methods.
View Cached Full Text
Cached at: 09/09/26, 04:30 AM
Paper page - SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution
Source: https://huggingface.co/papers/2609.05594
Abstract
SceneMosaic combines learned image priors with vision-language agents to efficiently generate diverse, physically valid indoor scenes by evolving local units and composing them globally.
Diverse and simulation-ready indoor scenes are essential for interactive entertainment and embodied AI, yet their scalable generation remains challenging. Recent agentic text-to-3D scene pipelines that rely onvision-language models(VLMs) can generate scenes of high fidelity but require costly iterative object placement and refinement. Another mainstream paradigm,parametric image-to-3D scene models, produces scenes efficiently from strong priors learned from 2D images but often leads to imprecise and physically invalid scenes. More importantly, both paradigms struggle to output diverse scenes for a single input, making it hard for them to reflect the dynamically changing nature of real scenes. In this paper we proposeSceneMosaic, a framework that combines the merits of both paradigms. It obtains the initial candidate from the learned image-based prior, and subsequently evolves the result through VLM agents, ensuring both efficiency and physical validity. Within the evolution process,SceneMosaicexploits the locality of natural scenes and decomposes a scene into independent local units, allowing separate evolution within each unit before composing the global scene viaCartesian product. OnSceneEval-100,SceneMosaicmatches the strongest agentic baseline insemantic layoutquality with a 24x speedup, substantially reducesphysical violations, and receives the highest human ratings. Our code is publicly available at https://github.com/rxjfighting/SceneMosaic.
View arXiv pageView PDFProject pageGitHub13Add to collection
Get this paper in your agent:
hf papers read 2609\.05594
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2609.05594 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2609.05594 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2609.05594 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene
Mira-Scene introduces a compositional 3D scene reconstruction framework using pixel-aligned canonical coordinate maps for accurate object layouts, achieving significant improvements in layout accuracy over existing methods.
Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator
Image2Sim is a neural simulation framework that creates high-fidelity interactive environments from RGB-D images, enabling scalable training for embodied navigation agents. It generates nearly 20K scenes and over 10 million training samples, showing strong benchmark improvements and effective real-world zero-shot transfer.
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling
Lucida proposes a method for composable indoor scene reconstruction that distributes requirements across parsing, generation, and placement using a VLM policy to create high-fidelity editable replicas from cluttered captures.
Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis
A novel MLLM-based agentic framework called Code-as-Room generates 3D indoor rooms by converting top-down images into executable Blender code through a structured execution harness with cross-stage memory to maintain context.
See Before You Code: Learning Visual Priors for Spatially Aware Educational Animation Generation
This paper introduces OmniManim, a render-feedback-aware framework for generating educational animations from natural language descriptions using large language models. It addresses visual defects like element overlap and misalignment by incorporating explicit visual planning, post-render diagnostics, and localized repair, demonstrating improved render quality on newly constructed datasets.