From 7781c91ee4ccfe2b0ad8b126fe2da02ae40e27a1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20P=C4=99=C5=9Bko?= Date: Wed, 26 Sep 2018 13:44:49 +0200 Subject: [PATCH] Change abstract --- frontend/templates/index.html | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/frontend/templates/index.html b/frontend/templates/index.html index 96d38f0..aa59363 100644 --- a/frontend/templates/index.html +++ b/frontend/templates/index.html @@ -30,7 +30,7 @@

Abstract

- Many recent works in the field of Neural Style Transfer showed that producing an image in the style of another image is possible. There are various possible applications to use such techniques like paintings style transfer or photo-realistic style transfer. In our project, we present end-to-end solution that transforms input video into a comic in just a few seconds. Our work consists of two main parts: keyframes extraction and comic style transfer. In the near future we would like to introduce next two parts: Comic Grid Layout Generation and Speech Extraction. + In our project, we present a Web-based working solution for video comixification - a task of converting a video into a comics. We split this task into two separate problems: (a) frame extraction and (b) style transfer. To extract meaningful, representative frames from the video we employ a keyframe extraction algorithm based on Reinforcement Learning, while for transferring the style into comics we implement a generative adversarial network (GANs) model. Since there have been many works published on the so-called neural style transfer, we evaluate them all on the very same task, namely frame comixification and select the most appropriate method. We examined different combinations of Adaptive Instance Normalization, Universal Style Transfer and GAN models and confront them to find their advantages and disadvantages in terms of qualitative and quantitative analysis. In the near future we would like to introduce next two parts: Comic Grid Layout Generation and Speech Extraction.