Xia Zeqing

Ph.D. from
Character Shape Computing Lab (CSCL)
Institute of Computer Science & Technology (ICST)
Peking University(PKU)

Education

• PhD Candidate in Computer Science (09/2016 - 01/2023)
  School of Electronic Engineering and Computer Science,
  Peking University

• Bachelor’s Degree in Chemistry (09/2012 - 07/2016)
  Yuanpei College,
  Peking University

• Bachelor’s Degree in Computer Science(09/2014 - 07/2016)
  School of Electronic Engineering and Computer Science,
  Peking University

Research Interest

My research interests focus on Computer Vision and Computer Graphics, and I’m currently working on deep learning techniques for character shape synthesis, including

• Character image generation
• Character contour simplification
• Vector glyph generation
• Handwritting synthesis

Publications

Zeqing Xia, Zhouhui Lian, Yingmin Tang, and Jianguo Xiao. 2018. As-compact-as-possible vectorization for character images. In SIGGRAPH Asia 2018 Technical Briefs (SA ‘18). ACM, New York, NY, USA, Article 5, 4 pages. DOI: https://doi.org/10.1145/3283254.3283283 [PPT][Supplymentary Materials]

Shusen Tang, Zeqing Xia, Zhouhui Lian, Yingmin Tang, and Jianguo Xiao. 2019. FontRNN: Generating Large-scale Chinese Fonts via Recurrent Neural Network. Computer Graphics Forum. The Eurographics Association and John Wiley & Sons Ltd. 38-Issue 7. DOI: https://doi.org/10.1111/cgf.13861 [Homepage]

Zeqing Xia, Bojun Xiong, Zhouhui Lian. 2023. VecFontSDF: Learning to Reconstruct and Synthesize High-quality Vector Fonts via Signed Distance Functions. CVPR 2023 Accepted.[Homepage]

Courses

Spring (2017~2022), Autumn(2022): Elementary Number Theory, as a TA

Contact Me

zeqing(dot)xia(at)pku(dot)edu(dot)cn