Unsupervised convolutional neural networks for motion estimation
Authors:
- 19 August 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1629-1633
Abstract
Traditional methods for motion estimation estimate the motion field F between a pair of images as the one that minimizes a predesigned cost function. In this paper, we propose a direct method and train a Convolutional Neural Network (CNN) that when, at test time, is given a pair of images as input it produces a dense motion field F at its output layer. In the absence of large datasets with ground truth motion that would allow classical supervised training, we propose to train the network in an unsupervised manner. The proposed cost function that is optimized during training, is based on the classical optical flow constraint. The latter is differentiable with respect to the motion field and, therefore, allows backpropagation of the error to previous layers of the network. Our method is tested on both synthetic and real image sequences and performs similarly to the state-of-the-art methods.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- FlowNet: Learning Optical Flow with Convolutional Networks2015
- EpicFlow: Edge-preserving interpolation of correspondences for optical flow2015
- DeepFlow: Large Displacement Optical Flow with Deep Matching2013
- A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind ThemInternational Journal of Computer Vision, 2013
- A Naturalistic Open Source Movie for Optical Flow Evaluation2012
- Global minimization of Markov random fields with applications to optical flowInverse Problems and Imaging, 2012
- Large Displacement Optical Flow: Descriptor Matching in Variational Motion EstimationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Tracking Endocardium Using Optical Flow along Iso-Value Curve2006
- Medical Image Registration and Interpolation by Optical Flow with Maximal Rigidity2006
- Lucas/Kanade Meets Horn/Schunck: Combining Local and Global Optic Flow MethodsInternational Journal of Computer Vision, 2005