SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution

Researchers introduced SceneMosaic, a hybrid agentic layout evolution method that generates diverse, simulation-ready indoor scenes more efficiently than existing vision-language-model pipelines, addressing scalability challenges for interactive entertainment and embodied AI.

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 on vision-language models VLMs can generate scenes of high fidelity but require costly iter