Empowering Vector Graphics with Consistently Arbitrary Viewing and View-dependent Visibility

2025/05/27 by Yidi Li, Li, Yidi, Jun Xiao +7
Computer Science · #Advanced Vision and Imaging #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #Data Visualization and Analytics #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2505.21377

openalex publication_date 2025/05/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This work presents a novel text-to-vector graphics generation approach, Dream3DVG, allowing for arbitrary viewpoint viewing, progressive detail optimization, and view-dependent occlusion awareness. Our approach is a dual-branch optimization framework, consisting of an auxiliary 3D Gaussian Splatting optimization branch and a 3D vector graphics optimization branch. The introduced 3DGS branch can bridge the domain gaps between text prompts and vector graphics with more consistent guidance. Moreover, 3DGS allows for progressive detail control by scheduling classifier-free guidance, facilitating guiding vector graphics with coarse shapes at the initial stages and finer details at later stages. We also improve the view-dependent occlusions by devising a visibility-awareness rendering module. Extensive results on 3D sketches and 3D iconographies, demonstrate the superiority of the method on different abstraction levels of details, cross-view consistency, and occlusion-aware stroke culling.

Citations

• TV-3DG: Mastering Text-to-3D Customized Generation with Visual Prompt
• Layered Image Vectorization via Semantic Simplification
• Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering
• NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation
• Text-to-Vector Generation with Neural Path Representation
• SketchINR: A First Look into Sketches as Implicit Neural Representations
• SVGDreamer: Text Guided SVG Generation with Diffusion Model
• LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching
• Text-to-3D with Classifier Score Distillation
• 3D Gaussian Splatting for Real-Time Radiance Field Rendering
• 3D Gaussian Splatting for Real-Time Radiance Field Rendering
• Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
• DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models
• DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation
• HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance
• ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
• IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers
• DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality
• Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation
• Zero-1-to-3: Zero-shot One Image to 3D Object
• NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Images
• Point-E: A System for Generating 3D Point Clouds from Complex Prompts
• Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization
• Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
• CLIPascene: Scene Sketching with Different Types and Levels of Abstraction
• VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models
• Magic3D: High-Resolution Text-to-3D Content Creation
• DreamFusion: Text-to-3D using 2D Diffusion
• Classifier-Free Diffusion Guidance
• High-Resolution Image Synthesis with Latent Diffusion Models
• High-Resolution Image Synthesis with Latent Diffusion Models
• CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders
• Learning Transferable Visual Models From Natural Language Supervision
• Im2Vec: Synthesizing Vector Graphics without Vector Supervision
• Score-Based Generative Modeling through Stochastic Differential Equations
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Discovering Pattern Structure Using Differentiable Compositing
• DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
• Denoising Diffusion Probabilistic Models
• Neural Contours: Learning to Draw Lines from 3D Shapes
• A Learned Representation for Scalable Vector Graphics
• The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
• A Neural Representation of Sketch Drawings
• Deep Residual Learning for Image Recognition
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• ImageNet classification with deep convolutional neural networks

Cited by

• ViewCraft3D: High-Fidelity and View-Consistent 3D Vector Graphics Synthesis

Related

• CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusion
• SVGDreamer: Text Guided SVG Generation with Diffusion Model
• Text-Guided Vector Graphics Customization
• StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis
• SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation