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...

Descripción completa

Detalles Bibliográficos
Autores principales: Karageorgos, Konstantinos, Dimou, Anastasios, Alvarez, Federico, Daras, Petros
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7412516/
https://www.ncbi.nlm.nih.gov/pubmed/32664442
http://dx.doi.org/10.3390/s20143855

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7412516/
https://www.ncbi.nlm.nih.gov/pubmed/32664442
http://dx.doi.org/10.3390/s20143855

Ejemplares similares