6 papers
Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback
Guotao Liang, Zhangcheng Wang, Juncheng Hu +5
Multimodal Large Language Models (MLLMs) have shown promising capabilities in generating Scalable Vector Graphics (SVG) via direct code synthesis. However, existing paradigms typic…
SEATrack: Simple, Efficient, and Adaptive Multimodal Tracker
Junbin Su, Ziteng Xue, Shihui Zhang +3
Parameter-efficient fine-tuning (PEFT) in multimodal tracking reveals a concerning trend where recent performance gains are often achieved at the cost of inflated parameter budgets…
AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling
Juncheng Hu, Ziteng Xue, Guotao Liang +5
We introduce AmodalSVG, a new framework for amodal image vectorization that produces semantically organized and geometrically complete SVG representations from natural images. Exis…
Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling
Ximing Xing, Ziteng Xue, Zhenxi Li +8
Recent large language models have shifted SVG generation from differentiable rendering optimization to autoregressive program synthesis. However, existing approaches still rely on…
Reason-SVG: Enhancing Structured Reasoning for Vector Graphics Generation with Reinforcement Learning
Ximing Xing, Ziteng Xue, Yandong Guan +3
Generating high-quality Scalable Vector Graphics (SVGs) is challenging for Large Language Models (LLMs), as it requires advanced reasoning for structural validity, semantic accurac…
SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation
Ximing Xing, Juncheng Hu, Ziteng Xue +5
Generating high-quality Scalable Vector Graphics (SVGs) from text remains a significant challenge. Existing LLM-based models that generate SVG code as a flat token sequence struggl…