SVGFaith: A Two-Layer Meta-Evaluation of Faithfulness Metrics for Text-to-SVG Generation
cs.CV, cs.CL
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/Yukinonooo/SVGFaith
Terminology
Sources
- SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation
- Neural Style Transfer for Vector Graphics
- AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling
- Qwen2.5-Coder Technical Report
- GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluation
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback
- SVGEditBench V2: A Benchmark for Instruction-based SVG Editing
- DINOv2: Learning Robust Visual Features without Supervision
- Rendering-Aware Reinforcement Learning for Vector Graphics Generation
- VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing
- StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Translation
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models
- Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
- SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation
- Reason-SVG: Enhancing Structured Reasoning for Vector Graphics Generation with Reinforcement Learning
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs