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

• URL: http://arxiv.org/abs/2609.13294v1
• Date: Wed, 09 Sep 2026 15:36:36 GMT
• Title: VectorHarness: Recovering Editable, Relation-Preserving Structure from Scientific Graphics
• Abstract summary: We present VectorHarness, a multi-agent framework for reconstruction that recovers components using type-appropriate native representations.<n>Experiments show that VectorHarness improves executable success and relation preservation, reduces avoidable fallback, and maintains high visual fidelity across heterogeneous graphics.
• Score: 13.178383449521261
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• GraLoD: Graphics-Inspired Continuous Level-of-Detail Learning for Image Restoration [54.85451496831771]
  We propose GraLoD, a plug-and-play framework that treats restoration scale as a spatially varying and stage-dependent variable.<n>GraLoD reuses the native encoder hierarchy, aligns its multi-scale features into a shared LOD representation space, and predicts a stage-conditioned LOD field at each decoder stage.<n>Experiments demonstrate consistent improvements in task-specific and all-in-one restoration.
  arXiv  Detail & Related papers  (2026-09-15T03:22:22Z)
• Figures as Programs: Recursive Generation of Editable Scientific Figures [79.78366479117878]
  Recent image-generation models can synthesize visually appealing figures, but producing a human-satisfactory result in a single generation step remains difficult.<n>We formulate textscFigTree, a textitmulti-agent system that automatically transforms scientific paper into a structured vector figure.<n>A render-critic refinement loop jointly inspects the rendered figure and its underlying program, enabling visual defects to be traced to specific statements and accurately repaired.
  arXiv  Detail & Related papers  (2026-09-01T09:53:47Z)
• DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable [10.070492917829995]
  We introduce DrawAI, comprising an agentic benchmark, DrawAI-Bench, and a reconstruction workflow, DrawAI-Flow.<n>We formulate image-to-editable reconstruction, which recovers a structured, directly manipulable artifact from an image while preserving its visual and semantic content.<n>The results show that reconstruction quality and costs vary substantially across model-harness configurations, while DrawAI-Flow consistently improves editable structure.
  arXiv  Detail & Related papers  (2026-08-01T09:05:06Z)
• ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition [60.25038184390257]
  ReDesign is an agentic framework that grows an editable layer hierarchy by selecting and composing specialized tools across modalities.<n>To evaluate editability at scale, we introduce the Figma Edit Replay Benchmark consisting of 909 raw Figma files and 14,796 controlled edit instructions that replay edits on reconstructed outputs.
  arXiv  Detail & Related papers  (2026-07-28T10:53:33Z)
• GARDEN: Gravity-Aligned Reconstruction of Disentangled ENvironments from RGB images [61.2170105836525]
  We propose an RGB-only framework that reformulates reconstruction as physically-grounded scene factorization and outputs a structured hybrid scene representation.<n>The resulting representation combines explicit rigid bodies with a decoupled background, enabling direct physics simulation while preserving visual realism.
  arXiv  Detail & Related papers  (2026-06-02T17:13:01Z)
• SemLayer: Semantic-aware Generative Segmentation and Layer Construction for Abstract Icons [53.57408001182251]
  SemLayer is a visual generation empowered pipeline that restores editable layered structures.<n>We formalize this problem as semantic layer construction for flattened vector art.<n>We demonstrate the effectiveness of SemLayer, enabling previously inapplicable to flattened vector graphics and establishing semantic layer reconstruction as a practical and valuable task.
  arXiv  Detail & Related papers  (2026-03-25T07:51:04Z)
• The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment [105.31858867473845]
  ImageCritic can be integrated into an agent framework to automatically detect inconsistencies and correct them with multi-round and local editing.<n>In experiments, ImageCritic can effectively resolve detail-related issues in various customized generation scenarios, providing significant improvements over existing methods.
  arXiv  Detail & Related papers  (2025-11-25T18:40:25Z)
• ReMix: Towards a Unified View of Consistent Character Generation and Editing [22.04681457337335]
  ReMix is a unified framework for character-consistent generation and editing.<n>It constitutes two core components: the ReMix Module and IP-ControlNet.<n>ReMix supports a wide range of tasks, including personalized generation, image editing, style transfer, and multi-condition synthesis.
  arXiv  Detail & Related papers  (2025-10-11T10:31:56Z)
• Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent [38.61468007698179]
  We propose a descriptive-prompt-based editing framework, named DescriptiveEdit.<n>The core idea is to re-frame instruction-based image editing' as reference-image-based text-to-image generation'
  arXiv  Detail & Related papers  (2025-08-28T07:45:08Z)
• High-Fidelity GAN Inversion for Image Attribute Editing [61.966946442222735]
  We present a novel high-fidelity generative adversarial network (GAN) inversion framework that enables attribute editing with image-specific details well-preserved. With a low bit-rate latent code, previous works have difficulties in preserving high-fidelity details in reconstructed and edited images. We propose a distortion consultation approach that employs a distortion map as a reference for high-fidelity reconstruction.
  arXiv  Detail & Related papers  (2021-09-14T11:23:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.