6 papers · 1 filter
RoMa-: What Feed-Forward 3D Models Know About Image Matching
David Nordström, Xinyue Zhang, Thibaut Loiseau +2
Learned image matching has experienced significant progress in recent years, culminating in robust and accurate matchers such as RoMa, whose robustness is often attributed to its u…
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…
FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelity
Yuchen Rao, Xuqian Ren, Yinyu Nie +4
Recovering complete 3D representations of objects from few casual image captures remains a significant challenge. Recent 3D generative models, particularly those based on Flow-Matc…
GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer
Sayan Deb Sarkar, Sinisa Stekovic, Vincent Lepetit +1
Transferring appearance to 3D assets using different representations of the appearance object - such as images or text - has garnered interest due to its wide range of applications…
Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understanding
Yuchen Rao, Stefan Ainetter, Sinisa Stekovic +2
High-level 3D scene understanding is essential in many applications. However, the challenges of generating accurate 3D annotations make development of deep learning models difficul…
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…