MaDis-Stereo: Enhanced Stereo Matching via Distilled Masked Image Modeling

In stereo matching, Convolutional Neural Networks (CNNs), a class of deep learning models designed to process grid-like data such as images, have traditionally served as the predominant architectures. Although Transformer-based stereo models have been studied recently, their performance still lags b...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	Jihye Ahn, Hyesong Choi, Soomin Kim, Dongbo Min
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	IEEE 2025-01-01
Σειρά:	IEEE Access
Θέματα:	Exponential moving average masked image modeling pseudo depth label stereo depth estimation
Διαθέσιμο Online:	https://ieeexplore.ieee.org/document/10836678/
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!