SceneMosaic: Hybrid Agentic Layout Evolution Generates Simulation-Ready Indoor Scenes
hkuhk · hf · 2026-09-09
An HKU team released SceneMosaic for efficiently generating diverse, physically valid, simulation-ready indoor scenes.
Method highlights:
- Combines learned image priors with vision-language agents
- Hybrid agentic layout evolution: evolves local units, then composes globally
- Targets simulation-ready scene outputs
Useful for robot simulation and embodied training data generation.
More from Embodied
- CosmoH2G: dataset and baseline for transferring hand demos to robot grippers — Hongxiang Zhao · 2026-09-09
- TANGO: whole-body VLA model navigates humanoid robots in cluttered spaces from sim data — Anqi Li · 2026-09-09
- whurley rides CyberCab robotaxi again: 'clean and comfortable,' calls it his next car — whurley · 2026-09-09
- Apple's foldable iPhone named iPhone Duo, $2,000 starting price, October launch — petefang · 2026-09-09
- Hanshow and X-EraLab bring embodied retail robots to nearly 70,000 stores worldwide — 量子位 · 2026-09-09
- Hyper3D WorldGen turns a single photo into a fully editable 3D scene — dr_cintas · 2026-09-09