UGC Approved Journal no 63975(19)

ISSN: 2349-5162 | ESTD Year : 2014
Call for Paper
Volume 11 | Issue 3 | March 2024

JETIREXPLORE- Search Thousands of research papers



WhatsApp Contact
Click Here

Published in:

Volume 7 Issue 5
May-2020
eISSN: 2349-5162

UGC and ISSN approved 7.95 impact factor UGC Approved Journal no 63975

7.95 impact factor calculated by Google scholar

Unique Identifier

Published Paper ID:
JETIR2005230


Registration ID:
231854

Page Number

632-641

Share This Article


Jetir RMS

Title

Analysis of Semantic and Stylistic Image Generation

Abstract

Semantic Image Generation refers to the task of generating photorealistic images conditioning on some input data. This task is carried out by a specific set of neural networks called Generative Adversarial Networks. These are a set of neural networks which work opposed to each other, evolving from each other’s successes. The generator is a convolution network that outputs some image, while the discriminator is a network that classifies said image. The job of the discriminator is to perfectly identify an image as fake or real, while the generator’s job is to try to produce realistic images. Combining Convolutional Neural Networks with a technique called Spatially Adaptive Normalization (which is similar to Batch Normalization), the results of semantic image generation tend to be less washed out, owing to the semantic information being “retained” throughout the network. Stylistic transfer is added by using Variational Auto Encoders, which take as in put an image and breaks it down into its latent space. The latent space is then used to transfer the input image’s style to the output of the semantic image generator. The results of our project have tended towards photorealism after about 50 epochs, with further training promising even better results. Transferring the learned networks to a mobile app, we will be able to allow users to create content of cities with minimal effort.

Key Words

Semantic Image Generation, GANs, Deep Learning

Cite This Article

"Analysis of Semantic and Stylistic Image Generation", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 5, page no.632-641, May-2020, Available :http://www.jetir.org/papers/JETIR2005230.pdf

ISSN


2349-5162 | Impact Factor 7.95 Calculate by Google Scholar

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 7.95 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Cite This Article

"Analysis of Semantic and Stylistic Image Generation", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 5, page no. pp632-641, May-2020, Available at : http://www.jetir.org/papers/JETIR2005230.pdf

Publication Details

Published Paper ID: JETIR2005230
Registration ID: 231854
Published In: Volume 7 | Issue 5 | Year May-2020
DOI (Digital Object Identifier):
Page No: 632-641
Country: Mumbai, Maharashtra, India .
Area: Engineering
ISSN Number: 2349-5162
Publisher: IJ Publication


Preview This Article


Downlaod

Click here for Article Preview

Download PDF

Downloads

0003041

Print This Page

Current Call For Paper

Jetir RMS