Unsupervised convolutional neural networks for motion estimation
This addresses motion estimation for computer vision applications, but it is incremental as it adapts classical constraints to neural networks without major breakthroughs.
The paper tackled motion estimation by training an unsupervised convolutional neural network to produce dense motion fields from image pairs, achieving performance similar to state-of-the-art methods on synthetic and real sequences.
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.