Search results
StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation. Yunjey Choi1,2 Minje Choi1,2 Munyoung Kim2,3 Jung-Woo Ha2 Sunghun Kim2,4 Jaegul Choo1,2. 1 Korea University 2 Clova AI Research, NAVER Corp.
Dec 4, 2019 · Yunjey Choi, Youngjung Uh, Jaejun Yoo, Jung-Woo Ha. A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of generated images and 2) scalability over multiple domains.
Introduction. A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of generated images and 2) scalability over multiple domains. Existing methods address either of the issues, having limited diversity or mul-tiple models for all domains.
TLDR. This paper proposes a novel method, SingleGAN, to perform multi-domain image-to-image translations with a single generator, and introduces the domain code to explicitly control the different generative tasks and integrate multiple optimization goals to ensure the translation. Expand.
Yunjey Choi, Youngjung Uh, Jaejun Yoo, Jung-Woo Ha; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 8188-8197. Abstract.
Sep 19, 2024 · View a PDF of the paper titled Multichannel-to-Multichannel Target Sound Extraction Using Direction and Timestamp Clues, by Dayun Choi and Jung-Woo Choi. We propose a multichannel-to-multichannel target sound extraction (M2M-TSE) framework for separating multichannel target signals from a multichannel mixture of sound sources. Target sound ...
Semantic Scholar profile for Jung-Woo Choi, with 68 highly influential citations and 90 scientific research papers.
