Search Results for author: Daniel Maurer

Found 5 papers, 1 papers with code

SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping

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.

Optical Flow Estimation

Structure-from-Motion-Aware PatchMatch for Adaptive 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).

Optical Flow Estimation

ProFlow: Learning to Predict Optical Flow

no code implementations3 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.

Optical Flow Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.