2 code implementations • CVPR 2021 • Austin Stone, Daniel Maurer, Alper Ayvaci, Anelia Angelova, Rico Jonschkowski
We present SMURF, a method for unsupervised learning of optical flow that improves state of the art on all benchmarks by $36\%$ to $40\%$ (over the prior best method UFlow) and even outperforms several supervised approaches such as PWC-Net and FlowNet2.
no code implementations • 16 Jan 2019 • Hui Men, Hanhe Lin, Vlad Hosu, Daniel Maurer, Andres Bruhn, Dietmar Saupe
visual quality of interpolated frames mostly based on optical flow estimation.
no code implementations • ECCV 2018 • Daniel Maurer, Nico Marniok, Bastian Goldluecke, Andres Bruhn
To this end, we propose a novel structure-from-motion-aware PatchMatch approach that, in contrast to existing matching techniques, combines two hierarchical feature matching methods: a recent two-frame PatchMatch approach for optical flow estimation (general motion) and a specifically tailored three-frame PatchMatch approach for rigid scene reconstruction (SfM).
no code implementations • 3 Jun 2018 • Daniel Maurer, Andrés Bruhn
By relating forward and backward motion these learned models not only allow to infer valuable motion information based on the backward flow, they also help to improve the performance at occlusions, where a reliable prediction is particularly useful.
Ranked #15 on Optical Flow Estimation on Sintel-clean
no code implementations • 22 May 2015 • Yong Chul Ju, Daniel Maurer, Michael Breuß, Andrés Bruhn
First, we propose a novel variational model that operates directly on the Cartesian depth.