Seen2Scene open-sourced: flow matching trained on real partial scans for 3D scene completion, ECCV 2026
angelaqdai · x · 2026-09-07
Researchers have open-sourced Seen2Scene, the first flow matching-based approach trained directly on incomplete real-world 3D scans for scene completion, accepted to ECCV 2026, with 200+ GitHub stars already.
- Key innovation: visibility-guided flow matching explicitly masks unknown regions in real scans, enabling learning from real partial observations instead of the complete synthetic 3D data prior methods rely on.
- Scenes are represented as truncated signed distance fields (TSDFs) in sparse grids, modeled by a sparse transformer that efficiently handles complex structures.
- Uses 3D layout boxes as conditioning input and flexibly supports other inputs like text, powering both scan completion and text-to-3D scene generation.
More from Multimodal
- TischEins, a large Midjourney SREF library, relaunches with new design after security outage — tisch_eins · 2026-10-26
- MOSS-Image-SFT 4-step distillation tops 16.5K downloads on Hugging Face — _akhaliq · 2026-10-26
- Claude Code can now edit videos: a 10-prompt workflow from raw footage to final cut — TawohAwa · 2026-10-26
- One-sentence 3D worlds turn cinematic with CineMap and TapNow — gizakdag · 2026-10-26
- No Camera Needed: Creator Builds an Entire World in CineMap and Directs It Into Cinema — gizakdag · 2026-10-26
- Kling vs. Seedance: the Chinese AI video model rivalry — DavidmComfort · 2026-10-26