We're sorry but this page doesn't work properly without JavaScript enabled. Please enable it to continue.
Feedback

Painting with GANs: Challenges and Technicalities of Neural Style Transfer

Formal Metadata

Title
Painting with GANs: Challenges and Technicalities of Neural Style Transfer
Subtitle
Building Artistic Artefacts using Generative Networks
Title of Series
Number of Parts
130
Author
License
CC Attribution - NonCommercial - ShareAlike 3.0 Unported:
You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal and non-commercial purpose as long as the work is attributed to the author in the manner specified by the author or licensor and the work or content is shared also in adapted form only under the conditions of this
Identifiers
Publisher
Release Date
Language

Content Metadata

Subject Area
Genre
Abstract
A lot of advancements are happening in the field of Deep Learning and Generative Adversarial Networks are one of them. We have seen GANs being applied for photo editing and in-painting, generating new image datasets and realistic photographs, increasing resolution of images (Super Resolution), and many more things. Some people have also exploited GANs for generating fake content. All the above-mentioned examples are result of a technique where the focus is to generate uncommon yet original samples from scratch. However, these examples have very less commercial applications and GANs are capable of doing much more. The focus of this talk is a technique called "Neural Style Transfer (NST)" which has numerous commercial applications in the gaming world, fashion/design industry, mobile applications, and many more fields. Challenges and technicalities of NSTs will be covered in great detail. We will teach the machines on how to paint images and utilize Style Transfer networks to generate artistic artefacts. The flow of the talk will be as follows: ~ Self Introduction [1 minute] ~ A Succinct Prelude to GANs [10 minutes] ~ Understanding Style Transfer [5 minutes] ~ Learning about Neural Style Transfer Networks [5 minutes] ~ Loss Functions: Content, Style, Total Variantion [10 minutes] ~ Code Walkthrough and Result Analysis [5 minutes] ~ Challenges and Applications [5 minutes] ~ Questions and Answers Session [3-4 minutes]