AI RESEARCH
Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
arXiv CS.CV
•
ArXi:2605.15923v1 Announce Type: new Modern image encoders achieve high generalization by decoupling semantic meaning from resolution, an ability yet to be fully realized in the 3D domain. We investigate the failure of 3D point cloud encoders to achieve similar generalization and find that existing models are highly sensitive to sampling resolution and scale changes, leading to significant performance degradation.