LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation

CVPR 2018  ·  Tak-Wai Hui, Xiaoou Tang, Chen Change Loy ·

FlowNet2, the state-of-the-art convolutional neural network (CNN) for optical flow estimation, requires over 160M parameters to achieve accurate flow estimation. In this paper we present an alternative network that outperforms FlowNet2 on the challenging Sintel final pass and KITTI benchmarks, while being 30 times smaller in the model size and 1.36 times faster in the running speed. This is made possible by drilling down to architectural details that might have been missed in the current frameworks: (1) We present a more effective flow inference approach at each pyramid level through a lightweight cascaded network. It not only improves flow estimation accuracy through early correction, but also permits seamless incorporation of descriptor matching in our network. (2) We present a novel flow regularization layer to ameliorate the issue of outliers and vague flow boundaries by using a feature-driven local convolution. (3) Our network owns an effective structure for pyramidal feature extraction and embraces feature warping rather than image warping as practiced in FlowNet2. Our code and trained models are available at .

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Optical Flow Estimation KITTI 2012 LiteFlowNet-ft Average End-Point Error 1.6 # 10
Optical Flow Estimation KITTI 2015 LiteFlowNet-ft Fl-all 9.38 # 13
Optical Flow Estimation Sintel-clean LiteFlowNet-ft Average End-Point Error 4.54 # 24
Optical Flow Estimation Sintel-final LiteFlowNet-ft Average End-Point Error 5.38 # 23


No methods listed for this paper. Add relevant methods here