I am a Ph.D. student in Software Engineering at Beihang University, advised by Prof. Qian Yu. My research focuses on deep generative models, vector art synthesis and robust machine learning.
Key Words: Vector Art, Text-to-SVG, Neural Rendering, SVG Diffusion, SVG LLM
π₯ News
- 2025.02: Β ππ Our paper SVGDreamer++ accepted by T-PAMI!
- 2024.02: Β ππ Our paper SVGDreamer accepted by CVPRβ2024!
- 2023.12: Β ππ We released the PyTorch-SVGRender. Pytorch-SVGRender is the go-to library for state-of-the-art differentiable rendering methods for SVG generation.
π Publications
SVGFusion: Scalable Text-to-SVG Generation via Vector Space Diffusion
Ximing Xing, Juncheng Hu, Jing Zhang, Dong Xu, Qian Yu
TL;DR: SVGFusion is a novel Text-to-SVG model that generates high-quality vector graphics by learning continuous latent space representations.
SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation
Ximing Xing, Qian Yu, Chuang Wang, Haitao Zhou, Jing Zhang, Dong Xu
TL;DR: Upgrade version of SVGDreamer: A new optimization-based Text-to-SVG method
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)
Empowering LLMs to Understand and Generate Complex Vector Graphics
Ximing Xing, Juncheng Hu, Guotao Liang, Jing Zhang, Dong Xu, Qian Yu
TL;DR: Unifying SVG generation and understanding via semantic tokens.
VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors
Juncheng Hu, Ximing Xing, Jing Zhang, Qian Yu
TL;DR: VectorPainter synthesizes text-guided vector graphics by imitating strokes.
SVGDreamer: Text Guided SVG Generation with Diffusion Model
Ximing Xing, Chuang Wang, Haitao Zhou, Jing Zhang, Dong Xu, Qian Yu
TL;DR: SVGDreamer introduces semantic-driven vectorization (SIVE) and particle-based distillation (VPSD) to generate editable, high-quality SVGs with better shape control and diversity.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models
Ximing Xing, Chuang Wang, Haitao Zhou, Jing Zhang, Qian Yu, Dong Xu
TL;DR: DiffSketcher pioneered the use of diffusion models for text-to-vector sketch generation.
Advances in Neural Information Processing Systems (NeurIPS), 2023
Ximing Xing, Chuang Wang, Haitao Zhou, Zhihao Hu, Chongxuan Li, Dong Xu, Qian Yu
TL;DR: Free training for sketch control image synthesis via Stochastic Differential Equations (SDEs).
A Graph-Based Method for Reasoning About Label Noise
HaiYang Zhang, Ximing Xing, Liang Liu
TL;DR: DualGraph, the first method for label noise processing based on graph neural networks.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
π Projects
Pytorch-SVGRender: A Differentiable Rendering Library for SVG Creation
π₯ Main Contributors: Ximing Xing, Juncheng Hu
TL;DR: SVG Differentiable Rendering: Generating vector graphics using neural networks. Support: text-to-SVG, Image-to-SVG, SVG Editing.
π Project | πCode | π€HuggingFace | πDocs
π Honors and Awards
- 2024.12 National Scholarship for Doctoral Students.
- 2021.12 National Scholarship.
π Professional Activities
-
Conference Reviewer
CVPR 2024, ECCV 2024, NIPS 2024, ACM MM 2024, AAAI 2025, CVPR 2025
-
Journal Reviewer
IJCV, IEEE T-VCG
π» Internships
-
2021.06 - 2021.11, Ant Group, research intern. HangZhou, China.
Dialogue System, Task-based Dialogue System based on Deep Reinforcement Learning