.png){kind=icon}
.png){kind=icon}
Return
Self-Supervised Optical Flow Estimation by Projective Bootstrap
.png){kind=icon}
PRE
AI
DOI：10.1109/TITS.2018.2873980.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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-t with the subsequent frame Xt+1 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.
Keywords:
Computer vision
image motion analysis
unsupervised learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
8.4
Papers:
9.5K
Citations:
6.3W