Chuang Wang (王闯)

I am a Master's student from Beihang University(BUAA). My supervisor is Associate Professor Qian Yu. And I am also an algorithm intern of AIsphere, where I work on video generation. My mentors are Dongdong Yu and Jinxiao Lin.

Recently, my research focuses on deep generative models(Diffusion models and its application) and sketch&SVG generation.

Email  /  Google Scholar  /  Github

profile photo

Publications (* equal contribution, corresponding author)

SVGDreamer: Text Guided SVG Generation with Diffusion Model
Xingming Xing, Haitao Zhou, Chuang Wang, Jing Zhang, Dong Xu, Qian Yu
Computer Vision and Pattern Recognition(CVPR), 2024
Paper / Code GitHub stars
DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models
Xingming Xing, Chuang Wang, Haitao Zhou, Jing Zhang, Qian Yu, Dong Xu
Neural Information Processing Systems (NeurIPS), 2023
Paper / Code GitHub stars
SketchInverter: Multi-Class Sketch-Based Image Generation via GAN Inversion
Zirui An, Jingbo Yu, Runtao Liu, Chuang Wang, Qian Yu
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023
Paper

Preprints (* equal contribution, corresponding author)

Inversion-by-Inversion: Exemplar-based Sketch-to-Photo Synthesis via Stochastic Differential Equations without Training
Xingming Xing, Chuang Wang, Haitao Zhou, Zhihao Hu, Chongxuan Li, Dong Xu, Qian Yu
arXiv, 2023
arXiv / Code GitHub stars

Projects

PyTorch-SVGRender

PyTorch-SVGRender is the go-to library for differentiable rendering methods in SVG generation. It supports a variety of vectorization methods, including: Image-to-SVG, Text-to-SVG, Text-to-Sketch.

Based on Pytorch, 2023
Project Page / Doc / Code GitHub stars

Work Experience

  • AIsphere (Algorithm Intern), 2023.05~Now.

    Main job content: The construction and tuning of the basic model of video generation; The construction of the controllable video generation pipeline.


Awards

  • Outstanding graduate of Beihang University, 2023


Professional activities

  • Reviewer for CVPR2024

  • Reviewer for ACM MM2024


Interests

  • History



Design and source code from Jon Barron.