CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion

Masked Image Modeling (MIM) has recently been established as a potent pre-training paradigm. A pretext task is constructed by masking patches in an input image, and this masked content is then predicted by a neural network using visible patches as sole input. This pre-training leads to state-of-the-...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Weinzaepfel, Philippe, Leroy, Vincent, Lucas, Thomas, Brégier, Romain, Cabon, Yohann, Arora, Vaibhav, Antsfeld, Leonid, Chidlovskii, Boris, Csurka, Gabriela, Revaud, Jérôme
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!