Implicit and Explicit Regularization for Optical Flow Estimation

Implicit and Explicit Regularization for Optical Flow Estimation

In this paper, two novel and practical regularizing methods are proposed to improve existing neural network architectures for monocular optical flow estimation. The proposed methods aim to alleviate deficiencies of current methods, such as flow leakage across objects and motion consistency within ri...

Full description

Bibliographic Details
Main Authors: Konstantinos Karageorgos, Anastasios Dimou, Federico Alvarez, Petros Daras
Format: Article
Language:English
Published: MDPI AG 2020-07-01
Series:Sensors
Subjects:
optical flow
regularization
semantic segmentation
motion consistency
coordconv
Online Access:https://www.mdpi.com/1424-8220/20/14/3855

Internet

https://www.mdpi.com/1424-8220/20/14/3855

Similar Items