Polis: 3D Self-Supervision at City Scale
Quick summary
arXiv:2608.29426v1 Announce Type: cross Abstract: Reliable semantic representations derived from city-scale 3D models are increasingly important for urban analysis, infrastructure monitoring, autonomous systems, and heritage conservation. However, urban scenes of large spatial extent captured through aerial surveying differ substantially from the indoor, object-level, and self-driving LiDAR data used to pretrain most 3D self-supervised models. We introduce Polis, to our knowledge the first application of Sketched Isotropic Gaussian Regularization (SIGReg) as an objective for a native point clo
Key takeaways
- arXiv:2608.29426v1 Announce Type: cross Abstract: Reliable semantic representations derived from city-scale 3D models are increasingly important for urban analysis, infrastructure monitoring, autonomous systems, and heritage conservation.
- However, urban scenes of large spatial extent captured through aerial surveying differ substantially from the indoor, object-level, and self-driving LiDAR data used to pretrain most 3D self-supervised models.
- We introduce Polis, to our knowledge the first application of Sketched Isotropic Gaussian Regularization (SIGReg) as an objective for a native point clo
Why it matters
“Polis: 3D Self-Supervision at City Scale” exposes the compute, energy and supply-chain layer behind model competition. Capacity shifts can influence model costs, service availability and the ability of smaller companies to compete.
Member comments