Search Results for author:
Found 5 papers, 1 papers with code
SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping
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.
Technical Report on Visual Quality Assessment for Frame Interpolation
visual quality of interpolated frames mostly based on optical flow estimation.
Structure-from-Motion-Aware PatchMatch for Adaptive Optical Flow Estimation
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).
ProFlow: Learning to Predict Optical Flow
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
Direct Variational Perspective Shape from Shading with Cartesian Depth Parametrisation
First, we propose a novel variational model that operates directly on the Cartesian depth.
