Cascade context encoder for improved inpainting

03/11/2018
by   Bartosz Zielinski, et al.
0

In this paper, we analyze if cascade usage of the context encoder with increasing input can improve the results of the inpainting. For this purpose, we train context encoder for 64x64 pixels images in a standard way and use its resized output to fill in the missing input region of the 128x128 context encoder, both in training and evaluation phase. As the result, the inpainting is visibly more plausible. In order to thoroughly verify the results, we introduce normalized squared-distortion, a measure for quantitative inpainting evaluation, and we provide its mathematical explanation. This is the first attempt to formalize the inpainting measure, which is based on the properties of latent feature representation, instead of L2 reconstruction loss.

READ FULL TEXT

page 3

page 4

research
05/03/2022

Comparison of CoModGANs, LaMa and GLIDE for Art Inpainting- Completing M.C Escher's Print Gallery

Digital art restoration has benefited from inpainting models to correct ...
research
10/08/2018

Probabilistic Semantic Inpainting with Pixel Constrained CNNs

Semantic inpainting is the task of inferring missing pixels in an image ...
research
04/25/2016

Context Encoders: Feature Learning by Inpainting

We present an unsupervised visual feature learning algorithm driven by c...
research
01/29/2018

Shift-Net: Image Inpainting via Deep Feature Rearrangement

Deep convolutional networks (CNNs) have exhibited their potential in ima...
research
03/27/2018

Structural inpainting

Scene-agnostic visual inpainting remains very challenging despite progre...
research
07/20/2018

Automatic Semantic Content Removal by Learning to Neglect

We introduce a new system for automatic image content removal and inpain...
research
06/15/2018

Controllable Semantic Image Inpainting

We develop a method for user-controllable semantic image inpainting: Giv...

Please sign up or login with your details

Forgot password? Click here to reset