Test-Time Adaptation for Optical Flow Estimation Using Motion Vectors
Due to the prohibitive cost as well as technical challenges in annotating ground-truth optical flow for large-scale realistic video datasets, the existing deep learning models for optical flow estimation mostly rely on synthetic data for training, which in turn may lead to significant performance de...
Ausführliche Beschreibung
Bibliographische Detailangaben
Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 32(2023) vom: 31., Seite 4977-4988
|
1. Verfasser: |
Ayyoubzadeh, Seyed Mehdi
(VerfasserIn) |
Weitere Verfasser: |
Liu, Wentao,
Kezele, Irina,
Yu, Yuanhao,
Wu, Xiaolin,
Wang, Yang,
Jin, Tang |
Format: | Online-Aufsatz
|
Sprache: | English |
Veröffentlicht: |
2023
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|
Schlagworte: | Journal Article |