Projects per year
Abstract
It is difficult to recover the motion field from a real-world footage given a mixture of camera shake and other photometric effects. In this paper we propose a hybrid framework by interleaving a Convolutional Neural Network (CNN) and a traditional optical flow energy. We first conduct a CNN architecture using a novel learnable directional filtering layer. Such layer encodes the angle and distance similarity matrix between blur and camera motion, which is able to enhance the blur features of the camera-shake footages. The proposed CNNs are then integrated into an iterative optical flow framework, which enable the capability of modeling and solving both the blind deconvolution and the optical flow estimation problems simultaneously. Our framework is trained end-to-end on a synthetic dataset and yields competitive precision and performance against the state-of-the-art approaches.
Original language | English |
---|---|
Pages (from-to) | 327-338 |
Number of pages | 12 |
Journal | Pattern Recognition |
Volume | 75 |
Early online date | 22 Apr 2017 |
DOIs | |
Publication status | Published - 1 Mar 2018 |
Keywords
- Convolutional Neural Network (CNN)
- Directional filtering
- Optical flow
- Video/image deblurring
ASJC Scopus subject areas
- Software
- Signal Processing
- Computer Vision and Pattern Recognition
- Artificial Intelligence
Fingerprint
Dive into the research topics of 'Learn to Model Blurry Motion via Directional Similarity and Filtering'. Together they form a unique fingerprint.Projects
- 2 Finished
-
Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA)
Cosker, D. (PI), Bilzon, J. (CoI), Campbell, N. (CoI), Cazzola, D. (CoI), Colyer, S. (CoI), Fincham Haines, T. (CoI), Hall, P. (CoI), Kim, K. I. (CoI), Lutteroth, C. (CoI), McGuigan, P. (CoI), O'Neill, E. (CoI), Richardt, C. (CoI), Salo, A. (CoI), Seminati, E. (CoI), Tabor, A. (CoI) & Yang, Y. (CoI)
Engineering and Physical Sciences Research Council
1/09/15 → 28/02/21
Project: Research council
-
Acquiring Complete and Editable Outdoor Models from Video and Images
Hall, P. (PI), Campbell, N. (CoI), Cosker, D. (CoI) & Yang, Y. (CoI)
Engineering and Physical Sciences Research Council
23/10/13 → 21/04/17
Project: Research council
Profiles
-
Darren Cosker
- Department of Computer Science - Professor
- Centre for the Analysis of Motion, Entertainment Research & Applications
- UKRI CDT in Accountable, Responsible and Transparent AI
- Visual Computing
- Bath Institute for the Augmented Human
Person: Research & Teaching, Affiliate staff