CANVAS: Consistency-Aware Navigation via Visual Adaptive Sampling for Long-Context Text-to-SVG Generation

2026-08-31

AI Summary

本文提出CANVAS方法，通过视觉自适应采样解决长文本生成SVG时的全局一致性问题，无需额外训练即可提升几何关系、布局等的一致性。

Abstract

Autoregressive large models have recently advanced Text-to-SVG generation from simple icons to complex, long-context graphics, yet standard autoregressive decoding often fails to maintain global consistency across geometry, layout, occlusion, and composition. We introduce CANVAS (Consistency-Aware Navigation via Visual Adaptive Sampling), a training-free, render-aware inference framework that combines power-sharpened trajectory likelihood with visual feedback from rendered futures and derives a stroke-wise navigation rule. It effectively estimates each candidate stroke's future value under a limited generation and rendering budget and adaptively allocates samples according to candidate uncertainty, decision influence, and rollout cost. Experiments across multiple autoregressive SVG backbones and complementary benchmarks demonstrate improvements in global consistency, which includes sound geometric relationships, spatial layouts, occlusion ordering, and overall composition, without additional training, demonstrating the effectiveness and generalization ability of our framework.

Problem

• Text-to-SVG
• global consistency
• autoregressive decoding
• geometry
• layout

Innovation

• Consistency-Aware Navigation
• Visual Adaptive Sampling
• Render-aware Inference
• Autoregressive SVG Generation
• Global Consistency