Optical Flow Estimation with Convolutional Neural Nets
Syed Tafseer Haider Shah, Xiang Xuezhi, Waqas Ahmed · Pattern Recognition and Image Analysis · 2021
Abstract In recent years, convolutional neural networks (CNNs) have been used for optical flow estimation with great success. Convolutional neural networks are multilayer’s structures, highly competent to estimate the complex, nonlinear transformation between input imagery and the output. At present, it is one of the top and dynamic research domains in image processing. Modern researchers of optical flow have combined numerous strategies and ideas from traditional methods with deep learning settings, consequently producing massive amount of work within few years. In this paper we present an analysis of deep learning methods for optical flow estimation. We highlight the important features, key components and discuss factors for benefits and limitations of deep learning schemes of optical flow estimation. We also compare the performance in terms of accuracy, size and training procedures of different models based on convolutional neural networks proposed by modern researchers.