A Survey of CNN-Based Techniques for Scene Flow Estimation

The analysis of 3D motion information is the key to solve various computer vision tasks. Scene flow estimation tackles the problem of obtaining the 3D motion field. In this paper, we review the recent scene flow estimation papers with a focus on learning-based methods. The problem formulation, challenges and applications are introduced. The existing datasets and performance metrics are presented. The reason behind learning-based methods replacing the traditional variational methods are discussed. CNN-based scene flow estimation methods are then categorized with respect to the level of supervision, data-availability and the number of steps involved in obtaining the results. The performance of different methods on the well known KITTI and FlyingThings3D datasets are tabulated. Their relative advantages and limitations are then analysed. Future trends and some open problems in the estimation of scene flow are discussed with special focus on the self-supervised methods that does not require labelled training data.

Automated summary

In this paper, a review of recent learning-based scene flow estimation papers is conducted, focusing on the problem formulation, challenges, applications, existing datasets and performance metrics. The shift from traditional variational methods to learning-based methods is discussed. CNN-based scene flow estimation methods are categorized based on supervision level, data availability, and number of steps involved. The performance of different methods on well-known datasets is compared, and their advantages and limitations are analyzed. Future trends and open problems, particularly in the area of self-supervised methods, are discussed.