Spatially-invariant style-codes controlled makeup transfer

• Main Authors: DENG, Han, HAN, Chu, CAI, Hongmin, HAN, Guoqiang, HE, Shengfeng
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2021
• 主題: Break down; Component wise; Features extraction; Reference image; Spatial informations; Spatial misalignments; Spatially invariants; Three-component; Transfer problems; Two-step extraction; Databases and Information Systems
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/8526; https://ink.library.smu.edu.sg/context/sis_research/article/9529/viewcontent/Spatially_Invariant_Style_Codes_Controlled_Makeup_Transfer.pdf

Transferring makeup from the misaligned reference image is challenging. Previous methods overcome this barrier by computing pixel-wise correspondences between two images, which is inaccurate and computational-expensive. In this paper, we take a different perspective to break down the makeup transfer...