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

Paper recorded by Signals 4 on 2026-09-01 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-01 on arXiv · recorded by Signals 4 on 2026-09-02

Category: cs.CV · 计算机视觉 · first seen 2026-09-02

Abstract

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 c

Read on arXiv →