8 citations · 16 across the 10 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Emergent Multi-View Geometry Through Self-Distillation
David Nordström, Thibaut Loiseau, Vincent Lepetit +3
Over a century ago, Henri Poincaré argued that a motionless observer cannot acquire the notion of space. Yet, most visual representation learning methods operate on individual imag…
cs.CV2026
Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison
Thibaut Loiseau, Guillaume Bourmaud, Vincent Lepetit
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 info…