ByteDance Releases Lucida for Composable Real-to-Sim Scene Modeling

ByteDance-Seed · hf · 2026-09-01

ByteDance introduces Lucida, a framework for composable real-to-sim scene modeling. It improves indoor scene reconstruction by distributing pipeline requirements across parsing, asset generation, and VLM-guided placement, achieving high-fidelity editable replicas from cluttered captures.

Original post →

More from Research

Research channel →