Learn to Model Motion from Blurry Footages
This addresses motion estimation in challenging real-world footage for computer vision applications, but it is incremental as it builds on existing optical flow and deconvolution techniques.
The paper tackles the problem of recovering motion fields from blurry videos with camera shake by proposing a hybrid framework that interleaves a CNN with a traditional optical flow energy, achieving competitive precision and performance against state-of-the-art methods.
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.