arxivst stuff from arxiv that you should probably bookmark

Learn to Model Motion from Blurry Footages

Abstract · Apr 19, 2017 16:54 ·

photometric directional footage blur flow motion camera shake optical cs-cv

Arxiv Abstract

  • Wenbin Li
  • Da Chen
  • Zhihan Lv
  • Yan Yan
  • Darren Cosker

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 modelling 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.

Read the paper (pdf) »