Self-Supervised Optical Flow Estimation by Projective Bootstrap

Abstract: Dense optical flow estimation is complex and time consuming, with state-of-the-art methods relying either on large synthetic data sets or on pipelines requiring up to a few minutes per frame pair. In this paper, we address the problem of optical flow estimation in the automotive scenario in a self-supervised manner. We argue that optical flow can be cast as a geometrical warping between two successive video frames and devise a deep architecture to estimate such transformation in two stages. First, a dense pixel-level flow is computed with a projective bootstrap on rigid surfaces. We show how such global transformation can be approximated with a homography and extend spatial transformer layers so that they can be employed to compute the flow field implied by such transformation. Subsequently, we refine the prediction by feeding a second, deeper network that accounts for moving objects. A final reconstruction loss compares the warping of frame X? with the subsequent frame X??? and guides both estimates. The model has the speed advantages of end-to-end deep architectures while achieving competitive performances, both outperforming recent unsupervised methods and showing good generalization capabilities on new automotive data sets.

Citation:

Alletto, Stefano; Abati, Davide; Calderara, Simone; Cucchiara, Rita; Rigazio, Luca "Self-Supervised Optical Flow Estimation by Projective Bootstrap" IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, vol. 20, pp. 3294 -3302 , 2019 DOI: 10.1109/TITS.2018.2873980

 not available

Paper download:

• Author version:
• DOI: 10.1109/TITS.2018.2873980