Few-Shot Image Synthesis using Noise-Based Deep Conditional Generative Adversarial Nets

• 발행기관: 한국스마트미디어학회
• 저자명: Finlyson Mwadambo Msiska Ammar Ul Hassan 최재영(Jaeyoung Choi) 유재원(Jaewon Yoo)
• 간행물 정보: 『스마트미디어저널』Vol10, No.1, 79~87쪽, 전체 9쪽
• 주제분류: 공학 > 컴퓨터학
• 파일형태: PDF
• 발행일자: 2021.03.30

영문 초록

In recent years research on automatic font generation with machine learning mainly focus on using transformation-based methods, in comparison, generative model-based methods of font generation have received less attention. Transformation-based methods learn a mapping of the transformations from an existing input to a target. This makes them ambiguous because in some cases a single input reference may correspond to multiple possible outputs. In this work, we focus on font generation using the generative model-based methods which learn the buildup of the characters from noise-to-image. We propose a novel way to train a conditional generative deep neural model so that we can achieve font style control on the generated font images. Our research demonstrates how to generate new font images conditioned on both character class labels and character style labels when using the generative model-based methods. We achieve this by introducing a modified generator network which is given inputs noise, character class, and style, which help us to calculate losses separately for the character class labels and character style labels. We show that adding the character style vector on top of the character class vector separately gives the model rich information about the font and enables us to explicitly specify not only the character class but also the character style that we want the model to generate.

목차

I. INTRODUCTION

II. RELATED WORKS

III. PROPOSED METHOD

IV. EXPERIMENTS

V. DISCUSSION

VI. CONCLUSION

키워드

font font styles computer vision image generation generative adversarial networks