Symmetric Skip Connection Wasserstein GAN for High-Resolution Facial Image Inpainting

01/11/2020
by   Jireh Jam, et al.
6

We propose a Symmetric Skip Connection Wasserstein Generative Adversarial Network (S-WGAN) for high-resolution facial image inpainting. The architecture is an encoder-decoder with convolutional blocks, linked by skip connections. The encoder is a feature extractor that captures data abstractions of an input image to learn an end-to-end mapping from an input (binary masked image) to the ground-truth. The decoder uses the learned abstractions to reconstruct the image. With skip connections, S-WGAN transfers image details to the decoder. Also, we propose a Wasserstein-Perceptual loss function to preserve colour and maintain realism on a reconstructed image. We evaluate our method and the state-of-the-art methods on CelebA-HQ dataset. Our results show S-WGAN produces sharper and more realistic images when visually compared with other methods. The quantitative measures show our proposed S-WGAN achieves the best Structure Similarity Index Measure of 0.94.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 6

research
08/29/2022

Rethinking Skip Connections in Encoder-decoder Networks for Monocular Depth Estimation

Skip connections are fundamental units in encoder-decoder networks, whic...
research
08/27/2018

Facial Information Recovery from Heavily Damaged Images using Generative Adversarial Network- PART 1

Over the past decades, a large number of techniques have emerged in mode...
research
09/05/2019

Poly-GAN: Multi-Conditioned GAN for Fashion Synthesis

We present Poly-GAN, a novel conditional GAN architecture that is motiva...
research
03/21/2020

Cross-modal Deep Face Normals with Deactivable Skip Connections

We present an approach for estimating surface normals from in-the-wild c...
research
11/29/2017

PSIque: Next Sequence Prediction of Satellite Images using a Convolutional Sequence-to-Sequence Network

Predicting unseen weather phenomena is an important issue for disaster m...
research
03/30/2021

Progressively Complementary Network for Fisheye Image Rectification Using Appearance Flow

Distortion rectification is often required for fisheye images. The gener...
research
05/01/2020

Image fusion using symmetric skip autoencodervia an Adversarial Regulariser

It is a challenging task to extract the best of both worlds by combining...

Please sign up or login with your details

Forgot password? Click here to reset