Guided Optical Flow Learning

Yi Zhu, Zhenzhong Lan, Shawn Newsam and Alexander G Hauptmann

May 12, 2017 (modified: May 12, 2017) CVPR 2017 BNMW Submission readers: everyone
  • Paper length: 4 page
  • Abstract: We study the unsupervised learning of CNNs for optical flow estimation using proxy ground truth data. Supervised CNNs, due to their immense learning capacity, have shown superior performance on a range of computer vision problems including optical flow prediction. They however require the ground truth flow which is usually not accessible except on limited synthetic data. Without the guidance of ground truth optical flow, unsupervised CNNs often perform worse as they are naturally ill-conditioned. We therefore propose a novel framework in which proxy ground truth data generated from classical approaches is used to guide the CNN learning. The models are further refined in an unsupervised fashion using an image reconstruction loss. Our guided learning approach is competitive with or superior to state-of-the-art approaches on three standard benchmarks yet is completely unsupervised and can run in real time.
  • Conflicts:
  • Keywords: Optical flow estimation, Unsupervised learning, Convolutional neural network