SOURCE-LINKED INTELLIGENCE

Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Self-supervised pre-training via cross-view completion learns strong features for 3D vision from co-visible regions of image pairs. However, the reference view provides little information for reconstructing non-co-visible patches, implicitly yielding a monocular training signal in these regions. We introduce Gekko, which turns this limitation into a useful signal. The relative improvement of the cross-view reconstruction error over a masked-autoencoder error is a self-supervised proxy for co-visibility: large improvements indicate co-visible regions, negligible ones non-co-visible areas. Gekko

Read original source ↗ Open in workspace

recordType

paper

region

Global