The image-to-image translation is one of the deep learning applications using image data. In this paper, we aim at improving the performance of object transfiguration which transforms a specific object in an image into another specific object. For object transfiguration, it is required to transform only the target object and maintain background images. In the existing results, however, it is observed that other parts in the image are also transformed. In this paper, we have focused on the structure of artificial neural networks that are frequently used in the existing methods and have improved the performance by adding constraints to the exiting structure. We also propose the advanced structure that combines the existing structures to maintain their advantages and complement their drawbacks. The effectiveness of the proposed methods are shown in experimental results.

Abstract
 1. 서 론
 2. 관련 연구
  2.1 GAN & Cycle-GAN
  2.2 Adversarial Loss
  2.3 Cycle-consistency Loss
  2.4 Full Objective
 3. 제안하는 방법
  3.1 구조적 제약을 추가한 Input-residual
  3.2 기존의 Residual-net과 U-net 분석
  3.3 Residual Block을 추가한 -net
 4. 실 험
  4.1 실험 방법
  4.2 데이터 세트
  4.3 배경 유지 성능을 평가하기 위한 정량적 지표
  4.4 정성적 평가
  4.5 배경 유지에 대한 정량적 평가
 5. 결 론
 References

• 김세운(School of Robotics, Kwangwoon University, Seoul, Korea) | Sewoon Kim
• 박광현(School of Robotics, Kwangwoon University, Seoul, Korea) | Kwang-Hyun Park Corresponding author