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.
More from Research
- TAAL Fixes Early Beam Pruning in Generative Recommendation — _reachsumit · 2026-09-01
- Strong/Weak Graph Edges Encode Opposite Relations in CF — _reachsumit · 2026-09-01
- REIGN Enables Efficient Context-Length Scaling for Retrieval — _reachsumit · 2026-09-01
- IBM Proposes Spatial Matryoshka Training for Multi-Granularity Document Retrieval — _reachsumit · 2026-09-01
- Doc-REFRAG: coarse-compress then selectively expand for faster, more accurate multi-image RAG — _reachsumit · 2026-09-01
- Google Releases RSLM: Training-Free Vector Quantization for ANN Search — _reachsumit · 2026-09-01