Unsupervised Learning of Sensory Primitives from Optical Flow Fields

2014 ◽  
pp. 188-197 ◽  
Author(s):  
Oswald Berthold ◽  
Verena V. Hafner
Keyword(s):  
Optical Flow ◽  
Unsupervised Learning ◽  
Flow Fields

Monocular Structure from Motion Based on Angular BA

2015 ◽  
Vol 742 ◽  
pp. 290-293
Author(s):  
Xiu Zhi Li ◽  
Ai Lin Yang ◽  
Huan Qiu ◽  
Song Min Jia
Keyword(s):  
Optical Flow ◽  
Structure From Motion ◽  
Structure Refinement ◽  
3D Structure ◽  
Flow Fields ◽  
Image Point ◽  
Pixel Pair ◽  
Pair Matching ◽  
Dense Correspondence

This paper presents a technique for monocular Structure from Motion (SFM) that reconstructs 3D world shape. The technique proposed uses optical flow for 2D pixel pair matching and Angular Bundle Ajustment (ABA) for 3D structure refinement. The proposed strategy has two main advantages. Firstly, optical flow fields provide sufficient dense correspondence of image point pairs and secondly, ABA outperforms classic BA variants, especially for the points relatively far from camera. The reconstruction results obtained in realistic scenario demonstrate the effectiveness and accuracy of the proposed algorithm.

Locating the singular point in first-order optical flow fields.

1998 ◽  
Vol 24 (5) ◽  
pp. 1415-1430 ◽  
Author(s):  
Susan F. te Pas ◽  
Astrid M. L. Kappers ◽  
Jan J. Koenderink
Keyword(s):  
Singular Point ◽  
Optical Flow ◽  
Flow Fields ◽  
First Order

OIFlow: Occlusion-Inpainting Optical Flow Estimation by Unsupervised Learning

2021 ◽  
pp. 1-1
Author(s):  
Shuaicheng Liu ◽  
Kunming Luo ◽  
Nianjin Ye ◽  
Chuan Wang ◽  
Jue Wanga ◽  
...  
Keyword(s):  
Optical Flow ◽  
Unsupervised Learning ◽  
Flow Estimation ◽  
Optical Flow Estimation
Sign in / Sign up

Export Citation Format

Share Document