【学术预告】Vectorization-based Color Transfer for Portrait Images-正规赌平台网址-全国十大赌博官网

正规赌平台网址

  • 科学研究Research

  • 研究机构
  • 学术动态
  • 人才培养Academic

  • 本科教育
  • 研究生教育
  • 研究生论坛
  • 实训就业
  • 海外经历
  • 学生工作Student

  • 本科
  • 研究生
  • 人才招聘Recruitment

  • 校友工作Alumni

  • 学院校友会管理办法
  • 杰出校友
  • 办公指南Guide

  • 规章制度
  • 院内信息Information

  • 学术动态

    当前位置: 首页 > 科学研究 > 学术动态 > 正文

    【学术预告】Vectorization-based Color Transfer for Portrait Images

    发布日期:2019-07-10    作者:     来源:     点击:

    题目: Vectorization-based Color Transfer for Portrait Images

    报告人:贺英,新加坡南洋理工大学计算机科学和工程系副教授

    时间:2019年7月13日 9:00am – 10:30am. 

    地点:办公楼310会议室

    摘要: I will introduce a method for transferring colors between portrait images. Using a trained neural network to extract facial mask, we vectorize each image with a set of sparse diffusion curves to encode the low-frequency colors, and use the Laplacian of residual colors to represent the high-frequency details. Then we apply optimal mass transport to transfer the boundary colors between the diffusion curves of the source and reference images. Finally, the original or modified Laplacians of colors are added to the transferred diffusion curve image. Unlike the existing methods that either require 3D information or assume the source and reference images have similar poses and dense correspondence, our method is computationally efficient and flexible, which can work for portrait images with large pose and color differences.

    报告人简介: Ying He is currently an associate professor at School of Computer Engineering, Nanyang Technological University, Singapore. He received the BS and MS degrees in electrical engineering from Tsinghua University, China, and the PhD degree in computer science from Stony Brook University, USA. His research interests fall into the general areas of visual computing and he is particularly interested in the problems which require geometric analysis and computation.

    地址:中国济南高新技术产业开发区舜华路1500号        邮编:250101

    电话:(86)-531-88391516        传真:(86)-531-88391686

    扫一扫
    关注公众号