InterpoNet, A brain inspired neural network for optical flow dense interpolation
This addresses a fundamental bottleneck in optical flow estimation for computer vision applications, offering a robust, data-driven solution with state-of-the-art performance.
The paper tackled the problem of sparse-to-dense interpolation for optical flow by proposing a fully convolutional network inspired by the visual cortex, which outperformed the state-of-the-art EpicFlow method, achieving top results on Sintel and KITTI 2012 benchmarks.
Sparse-to-dense interpolation for optical flow is a fundamental phase in the pipeline of most of the leading optical flow estimation algorithms. The current state-of-the-art method for interpolation, EpicFlow, is a local average method based on an edge aware geodesic distance. We propose a new data-driven sparse-to-dense interpolation algorithm based on a fully convolutional network. We draw inspiration from the filling-in process in the visual cortex and introduce lateral dependencies between neurons and multi-layer supervision into our learning process. We also show the importance of the image contour to the learning process. Our method is robust and outperforms EpicFlow on competitive optical flow benchmarks with several underlying matching algorithms. This leads to state-of-the-art performance on the Sintel and KITTI 2012 benchmarks.