ByteDance Lucida: Composable Real-to-Sim Scene Modeling
janusch_patas · x · 2026-09-01
ByteDance introduces Lucida, a composable Real-to-Sim scene modeling method that transforms real-world indoor scans into editable 3D asset collections for robotics simulation. The pipeline consists of three stages:
- Parse: Extracts instance evidence from multi-view observations to build a scene graph.
- Generate: Synthesizes occlusion-free object images and lifts them into complete 3D assets.
- Place: Refines poses via closed-loop GizmoAct to align rendered assets with the captured scene.
Collaboration between ByteDance Seed, Peking University, and Zhejiang University.
Related event: ByteDance's Lucida Turns Indoor Video into Editable 3D Simulation Scenes(4 posts)→
More from Embodied
- SimInfinity: open-source robotic simulation benchmark with 10K real-world tasks — joemeno · 2026-10-18
- Robi: a German/English voice companion demo built on Gemma, Tyger and Humaneness Voice TTS — realmrfakename · 2026-10-18
- Munich's Plim unveils wheeled home-care humanoid controllable from 9,000 km away — CyberRobooo · 2026-10-18
- Musk says Optimus and Cybercab will make up the vast majority of Tesla's value — XFreeze · 2026-10-18
- SAE weight editing steers robot behavior at inference time, IIIT Hyderabad paper lands IJCAI Safe Physical AI workshop — ponguru · 2026-10-18
- NTU-led survey reviews nearly 200 papers on affordance learning for embodied AI — jiqizhixin · 2026-10-18