Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching

Despite the great success of deep learning in stereo matching, recovering accurate disparity maps is still challenging. Currently, L1 and cross-entropy are the two most widely used losses for stereo network training. Compared with the former, the latter usually performs better thanks to its probabil...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Xu, Peng, Xiang, Zhiyu, Qiao, Chenyu, Fu, Jingyun, Pu, Tianyu
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!