Author name: Louis Martinez, Maks Ovsjanikov

arXiv:2604.22334v2 Announce Type: replace
Abstract: Recent advances in pretraining 3D point cloud encoders (e.g., Point-BERT, Point-MAE) have produced powerful models, whose abilities are typically evaluated on geometric or semantic tasks. At the same…

arXiv:2604.22334v1 Announce Type: new
Abstract: Recent advances in pretraining 3D point cloud encoders (e.g., Point-BERT, Point-MAE) have produced powerful models, whose abilities are typically evaluated on geometric or semantic tasks. At the same tim…