DeepAI
Log In Sign Up

Light-weight pixel context encoders for image inpainting

01/17/2018
by   Nanne van Noord, et al.
0

In this work we propose Pixel Content Encoders (PCE), a light-weight image inpainting model, capable of generating novel con-tent for large missing regions in images. Unlike previously presented convolutional neural network based models, our PCE model has an order of magnitude fewer trainable parameters. Moreover, by incorporating dilated convolutions we are able to preserve fine grained spatial information, achieving state-of-the-art performance on benchmark datasets of natural images and paintings. Besides image inpainting, we show that without changing the architecture, PCE can be used for image extrapolation, generating novel content beyond existing image boundaries.

READ FULL TEXT

page 1

page 6

page 7

page 8

page 9

07/26/2016

Semantic Image Inpainting with Deep Generative Models

Semantic image inpainting is a challenging task where large missing regi...
10/02/2018

Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks

Deep neural networks, in particular convolutional neural networks, have ...
04/25/2016

Context Encoders: Feature Learning by Inpainting

We present an unsupervised visual feature learning algorithm driven by c...
10/28/2022

Thermal Infrared Image Inpainting via Edge-Aware Guidance

Image inpainting has achieved fundamental advances with deep learning. H...
07/21/2020

Enhancement of damaged-image prediction through Cahn-Hilliard Image Inpainting

We assess the benefit of including an image inpainting filter before pas...
10/29/2020

Free-Form Image Inpainting via Contrastive Attention Network

Most deep learning based image inpainting approaches adopt autoencoder o...
05/05/2021

PD-GAN: Probabilistic Diverse GAN for Image Inpainting

We propose PD-GAN, a probabilistic diverse GAN for image inpainting. Giv...