Perceiving Systems, Computer Vision

PCA-Flow: Fast, approximate optical flow computation

2015-06-01


This software package contains two algorithms for the computation of optical flow, as described in Wulff & Black, "Efficient Sparse-to-Dense Optical Flow Estimation using a Learned Basis and Layers" (CVPR 2015). PCA-Flow computes approximate optical flow extremely quickly, by making the assumption that optical flow lies on a low-dimensional subspace. PCA-Layers extends this to a layered model to increase accuracy, especially at boundaries. It is the most accurate layered model on the MPI Sintel dataset.

Author(s): Jonas Wulff and Michael J. Black
Department(s): Perceiving Systems
Publication(s): Efficient Sparse-to-Dense Optical Flow Estimation using a Learned Basis and Layers
Authors: Jonas Wulff and Michael J. Black
Release Date: 2015-06-01
External Link: https://github.com/jswulff/pcaflow