501 citations · 1k across the 33 of their papers we have counts for
Showing 2018 · cs.CVShow all
2 papers · 2 filters
cs.CV2018★ 16 cited
SEIGAN: Towards Compositional Image Generation by Simultaneously Learning to Segment, Enhance, and Inpaint
Pavel Ostyakov, Roman Suvorov, Elizaveta Logacheva +2
We present a novel approach to image manipulation and understanding by simultaneously learning to segment object masks, paste objects to another background image, and remove them f…
cs.CV2018
Label Denoising with Large Ensembles of Heterogeneous Neural Networks
Pavel Ostyakov, Elizaveta Logacheva, Roman Suvorov +4
Despite recent advances in computer vision based on various convolutional architectures, video understanding remains an important challenge. In this work, we present and discuss a…