2 papers
cs.CV2019
A nonlocal feature-driven exemplar-based approach for image inpainting
Viktor Reshniak, Jeremy Trageser, Clayton G. Webster
We present a nonlocal variational image completion technique which admits simultaneous inpainting of multiple structures and textures in a unified framework. The recovery of geomet…
cs.LG2019
Robust learning with implicit residual networks
Viktor Reshniak, Clayton Webster
In this effort, we propose a new deep architecture utilizing residual blocks inspired by implicit discretization schemes. As opposed to the standard feed-forward networks, the outp…