PDC-Net+: Enhanced Probabilistic Dense Correspondence Network

Establishing robust and accurate correspondences between a pair of images is a long-standing computer vision problem with numerous applications. While classically dominated by sparse methods, emerging dense approaches offer a compelling alternative paradigm that avoids the keypoint detection step. H...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2023-08, Vol.45 (8), p.10247-10266
Hauptverfasser:	Truong, Prune, Danelljan, Martin, Timofte, Radu, Van Gool, Luc
Format:	Artikel
Sprache:	eng
Schlagworte:	3D reconstruction Algorithms Computer vision Correspondence estimation dense flow regression Estimation geometric matching Image manipulation Image reconstruction Image retrieval image-based localization Optical flow Optical flow (image analysis) Outliers (statistics) Pattern Recognition, Automated - methods Pose estimation Predictions probabilistic flow Probabilistic logic Probabilistic models Reliability Robustness Task analysis Training Uncertainty uncertainty estimation
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!