Faster Unsupervised Semantic Inpainting: A GAN Based Approach

08/14/2019
by   Avisek Lahiri, et al.
0

In this paper, we propose to improve the inference speed and visual quality of contemporary baseline of Generative Adversarial Networks (GAN) based unsupervised semantic inpainting. This is made possible with better initialization of the core iterative optimization involved in the framework. To our best knowledge, this is also the first attempt of GAN based video inpainting with consideration to temporal cues. On single image inpainting, we achieve about 4.5-5× speedup and 80× on videos compared to baseline. Simultaneously, our method has better spatial and temporal reconstruction qualities as found on three image and one video dataset.

READ FULL TEXT

page 3

page 4

research
08/16/2019

The Angel is in the Priors: Improving GAN based Image and Sequence Inpainting with Better Noise and Structural Priors

Contemporary deep learning based inpainting algorithms are mainly based ...
research
10/20/2018

Improved Techniques for GAN based Facial Inpainting

In this paper we present several architectural and optimization recipes ...
research
10/30/2020

PIINET: A 360-degree Panoramic Image Inpainting Network Using a Cube Map

Inpainting has been continuously studied in the field of computer vision...
research
12/08/2018

Face Completion with Semantic Knowledge and Collaborative Adversarial Learning

Unlike a conventional background inpainting approach that infers a missi...
research
03/31/2022

A Temporal Learning Approach to Inpainting Endoscopic Specularities and Its effect on Image Correspondence

Video streams are utilised to guide minimally-invasive surgery and diagn...
research
12/23/2019

Image Outpainting and Harmonization using Generative Adversarial Networks

Although the inherently ambiguous task of predicting what resides beyond...
research
05/26/2022

Semantically Supervised Appearance Decomposition for Virtual Staging from a Single Panorama

We describe a novel approach to decompose a single panorama of an empty ...

Please sign up or login with your details

Forgot password? Click here to reset