AI TrackerFrontier desk · AEST
Back to news
normalaitech

SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning

arXiv cs.AI · 24 Oct 2026, 03:59 AEST

SceneBloom is a new framework designed for generating realistic and diverse indoor environments for embodied learning. It combines visual layout sampling with contract-guided 3D compilation to create high-quality, physically stable scenes.

Key facts

Read aloud

SceneBloom is a new framework designed for generating realistic and diverse indoor environments for embodied learning. It combines visual layout sampling with contract-guided 3D compilation to create high-quality, physically stable scenes. Training generalizable embodied agents requires realistic, varied, and simulation-ready indoor environments. A hierarchical sampler uses diffusion priors to generate furniture arrangements within functional zones. Across five room types, SceneBloom attains the highest visual quality and physical stability among the compared methods and is the only method with no detected mesh collisions and out-of-bounds objects.

Sources in this cluster