Abstract
Motion in the image plane is ultimately a function of 3D motion in space. We propose to compute optical flow using what is os- tensibly an extreme overparameterization: depth, surface normal, and frame-to-frame 3D rigid body motion at every pixel, giving a total of 9 DoF. The advantages of such an overparameterization are twofold: first, geometrically meaningful reasoning can be called upon in the optimiza- tion, reflecting possible 3D motion in the underlying scene; second, the ‘fronto-parallel’ assumption implicit in the use of traditional matching pixel windows is ameliorated because the parameterization determines a plane-induced homography at every pixel. We show that optimization over this high-dimensional, continuous state space can be carried out using an adaptation of the recently introduced PatchMatch Belief Prop- agation (PMBP) energy minimization algorithm, and that the resulting flow fields compare favorably to the state of the art on a number of small- and large-displacement datasets.