Seen2Scene is the first flow matching model trained directly on incomplete real-world 3D scans rather than synthetic complete data.
March 31, 2026
Original Paper
Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow
arXiv · 2603.28548
The Takeaway
By utilizing visibility-guided flow to mask unknown regions, it breaks the dependency on synthetic datasets for 3D scene completion, enabling models to learn from real-world, cluttered observations.
From the abstract
We present Seen2Scene, the first flow matching-based approach that trains directly on incomplete, real-world 3D scans for scene completion and generation. Unlike prior methods that rely on complete and hence synthetic 3D data, our approach introduces visibility-guided flow matching, which explicitly masks out unknown regions in real scans, enabling effective learning from real-world, partial observations. We represent 3D scenes using truncated signed distance field (TSDF) volumes encoded in spar