Perceptual Loss for Convolutional Neural Network Based Optical Flow Estimation
Zongqing Lu, Zhu Xiang, Qingmin Liao · DEStech Transactions on Computer Science and Engineering · 2017
Convolutional Neural Networks (CNNs) are successfully used in optical flow estimation as learned patch based descriptors. In this work, rather training feature descriptors via CNNs, an end-to-end fully convolutional network, is developed for solving optical flow from a pair of images. Motivated by the success in image transformation tasks, a perceptual loss function is used for training the network for optical flow estimation. We trained a deep convolutional auto-encoder of optical flow field to obtain the high-level representation of motion structures rather than image texture. The perceptual loss function is then defined by high-level features extracted from the pretrained encoder. Conventional variational refinement are not performed. Experiments show the network achieves competitive performance on the challenging MPI Sintel set and Flying Chairs set.