2 papers
cs.CV2025
MuM: Multi-View Masked Image Modeling for 3D Vision
David Nordström, Johan Edstedt, Fredrik Kahl +1
Self-supervised learning on images seeks to extract meaningful visual representations from unlabeled data. When scaled to large datasets, this paradigm has achieved state-of-the-ar…
cs.CV2025
DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection
Johan Edstedt, Georg Bökman, Mårten Wadenbäck +1
Keypoints are what enable Structure-from-Motion (SfM) systems to scale to thousands of images. However, designing a keypoint detection objective is a non-trivial task, as SfM is no…