Generating a fusion image : one's identity and another's shape = 입력 이미지의 고유성과 모양을 보존하는 합성 이미지 생성에 관한 연구one's identity and another's shape

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 271
  • Download : 0
Generating a novel image by manipulating two input images is an interesting research problem in the study of generative adversarial networks (GANs). We propose a new GAN-based network that generates a fusion image with the identity of input image x and the shape of input image y. Our network can simultaneously train on more than two image datasets in an unsupervised manner. We define an identity loss $L_I$ to catch the identity of image x and a shape loss $L_S$ to get the shape of y. In addition, we propose a novel training method called Min-Patch training to focus the generator on crucial parts of an image, rather than its entirety. We show qualitative results on the VGG Youtube Pose dataset, Eye dataset (MPIIGaze and UnityEyes), and the Photo–Sketch–Cartoon dataset.
Advisors
Kim, Junmoresearcher김준모researcher
Description
한국과학기술원 :로봇공학학제전공,
Publisher
한국과학기술원
Issue Date
2018
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 로봇공학학제전공, 2018.8,[iii, 18 p. :]

Keywords

Deep learning▼amachine learning▼acomputer vision▼agenerative model▼aGenerative Adversarial Networks; 딥러닝▼a머신러닝▼a컴퓨터 비젼▼a생성 모델▼aGAN

URI
http://hdl.handle.net/10203/266002
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=828469&flag=dissertation
Appears in Collection
RE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0