ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition

• URL: http://arxiv.org/abs/2607.25565v1
• Date: Tue, 28 Jul 2026 10:53:33 GMT
• Title: ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition
• Abstract summary: 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.
• Score: 60.25038184390257
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recovering an editable design file from a raster image is a common and costly bottleneck in modern design workflows, yet remains challenging since editability depends on recovering multi-modal attributes, such as typography, vector geometry, colors, grouping, and layer ordering. We present ReDesign, an agentic framework that grows an editable layer hierarchy by selecting and composing specialized tools across modalities. To keep this long decision process reliable despite imperfect tool outputs, we introduce graceful verification at each expansion, which provides local accept, prune, or retry feedback that prevents error accumulation and avoids large scale reruns. 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. Across this benchmark and standard reconstruction metrics, ReDesign achieves strong visual fidelity while delivering the highest editability across layout, color, and text edits, outperforming layered decomposition baselines and serial tool use pipelines.

Related papers

• VectorHarness: Recovering Editable, Relation-Preserving Structure from Scientific Graphics [13.178383449521261]
  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.
  arXiv  Detail & Related papers  (2026-09-09T15:36:36Z)
• Towards Robust Sequential Decomposition for Complex Image Editing [26.747812783393204]
  We develop a synthetic data pipeline that constructs editing tasks of varying complexity, allowing us to curate a large-scale editing dataset with high-quality decomposed sequences.<n>By finetuning on synthetic data, we discovered that with properly designed editing paradigms, sequential decomposition yields robust improvements even as task complexity increases.
  arXiv  Detail & Related papers  (2026-05-10T00:23:05Z)
• CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator [8.901958956012072]
  Conditional image editing is crucial in scenarios requiring strict structural control.<n>Most approaches rely on single-step generation.<n>We propose textbfCAMEO, a structured multi-agent framework that reformulates conditional editing as a quality-aware, feedback-driven process.
  arXiv  Detail & Related papers  (2026-04-03T16:27:02Z)
• ReLayout: Versatile and Structure-Preserving Design Layout Editing via Relation-Aware Design Reconstruction [26.78568275114657]
  We focus on a foundational redesign task termed design layout editing.<n>We introduce four basic and important editing actions and standardize the format of editing operations.<n>We present Re, a novel framework for versatile structure-aware design editing that operates without triplet data.
  arXiv  Detail & Related papers  (2026-02-01T06:05:44Z)
• FlowDC: Flow-Based Decoupling-Decay for Complex Image Editing [52.54102743380658]
  We propose FlowDC, which decouples the complex editing into multiple sub-editing effects and superposes them in parallel during the editing process.<n>FlowDC shows superior results compared with existing methods.
  arXiv  Detail & Related papers  (2025-12-12T09:08:39Z)
• Image Editing As Programs with Diffusion Models [69.05164729625052]
  We introduce Image Editing As Programs (IEAP), a unified image editing framework built upon the Diffusion Transformer (DiT) architecture.<n>IEAP approaches instructional editing through a reductionist lens, decomposing complex editing instructions into sequences of atomic operations.<n>Our framework delivers superior accuracy and semantic fidelity, particularly for complex, multi-step instructions.
  arXiv  Detail & Related papers  (2025-06-04T16:57:24Z)
• Lost in Edits? A $λ$-Compass for AIGC Provenance [119.95562081325552]
  We propose a novel latent-space attribution method that robustly identifies and differentiates authentic outputs from manipulated ones.<n>LambdaTracer is effective across diverse iterative editing processes, whether automated through text-guided editing tools such as InstructPix2Pix or performed manually with editing software such as Adobe Photoshop.
  arXiv  Detail & Related papers  (2025-02-05T06:24:25Z)
• INRetouch: Context Aware Implicit Neural Representation for Photography Retouching [54.17599183365242]
  We propose a novel retouch transfer approach that learns from professional edits through before-after image pairs.<n>We develop a context-aware Implicit Neural Representation that learns to apply edits adaptively based on image content and context.<n>Our method extracts implicit transformations from reference edits and adaptively applies them to new images.
  arXiv  Detail & Related papers  (2024-12-05T03:31:48Z)
• Task-Oriented Diffusion Inversion for High-Fidelity Text-based Editing [60.730661748555214]
  We introduce textbfTask-textbfOriented textbfDiffusion textbfInversion (textbfTODInv), a novel framework that inverts and edits real images tailored to specific editing tasks. ToDInv seamlessly integrates inversion and editing through reciprocal optimization, ensuring both high fidelity and precise editability.
  arXiv  Detail & Related papers  (2024-08-23T22:16:34Z)

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.