8 citations · 16 across the 10 of their papers we have counts for
11 papers · 1 filter
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…
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…
Handling Multiple Hypotheses in Coarse-to-Fine Dense Image Matching
Matthieu Vilain, Rémi Giraud, Yannick Berthoumieu +1
Dense image matching aims to find a correspondent for every pixel of a source image in a partially overlapping target image. State-of-the-art methods typically rely on a coarse-to-…
Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regression
Thibaut Loiseau, Guillaume Bourmaud, Vincent Lepetit
Pre-training techniques have greatly advanced computer vision, with CroCo's cross-view completion approach yielding impressive results in tasks like 3D reconstruction and pose regr…
RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges
Thibaut Loiseau, Guillaume Bourmaud
Camera pose estimation is crucial for many computer vision applications, yet existing benchmarks offer limited insight into method limitations across different geometric challenges…
Are Semi-Dense Detector-Free Methods Good at Matching Local Features?
Matthieu Vilain, Rémi Giraud, Hugo Germain +1
Semi-dense detector-free approaches (SDF), such as LoFTR, are currently among the most popular image matching methods. While SDF methods are trained to establish correspondences be…