VectorHarness: Recovering Editable, Relation-Preserving Structure from Scientific Graphics

2026-09-09

AI Summary

为解决科学图形转换为可编辑代码的问题，提出VectorHarness框架，使用多代理方法恢复图形的原生可编辑结构。

Abstract

Converting scientific graphics into editable representations remains a challenging problem for image-to-code generation because of their heterogeneous elements and complex layouts. Recent multi-agent reconstruction systems have advanced this line of work, but often follow a copy-paste paradigm: the reconstructed image closely resembles the original, while complex regions remain effectively uneditable. We instead formulate a different objective, raster-to-authoring reconstruction, which aims to recover an authoring representation that supports native, customized editing rather than mere visual replication. To this end, we present VectorHarness, a multi-agent framework for raster-to-authoring reconstruction that recovers heterogeneous components using type-appropriate native representations. Text, formulas, shapes, connectors, icons, charts, and tables are reconstructed as natively editable objects, while intrinsically image-based regions remain raster content. To systematically evaluate reconstruction quality, we introduce VectorHarness-Bench, which jointly assesses rendering fidelity, raster fallback coverage, executable object edits, and relation-preserving edits. Experiments show that VectorHarness improves executable edit success and relation preservation, reduces avoidable raster fallback, and maintains high visual fidelity across heterogeneous graphics.

Problem

• scientific graphics
• editable representations
• heterogeneous elements
• complex layouts
• raster-to-authoring reconstruction

Innovation

• raster-to-authoring reconstruction
• editable objects
• relation-preserving edits
• multi-agent framework