DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable

• URL: http://arxiv.org/abs/2608.00548v1
• Date: Sat, 01 Aug 2026 09:05:06 GMT
• Title: DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable
• Abstract summary: 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.
• Score: 10.070492917829995
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent image-generation models and multimodal agents can produce high-quality visuals for increasingly complex visual communication tasks. Yet their raster outputs remain difficult to use directly because meaningful content and relationships are flattened into pixels, preventing users from inspecting, modifying, rearranging, or reusing individual components. We formulate image-to-editable reconstruction, which recovers a structured, directly manipulable artifact from a raster image while preserving its visual and semantic content. The central challenge is to jointly satisfy Fidelity and Editability, which often trade off in practice. To study this task, we introduce DrawAI, comprising an agentic benchmark, DrawAI-Bench, and a reconstruction workflow, DrawAI-Flow. DrawAI-Bench spans scientific figures, presentation slides, posters, and diagrams, combining real and AI-generated images to reflect practical visual-creation scenarios. It evaluates Fidelity and Editability through a hybrid protocol of 39 criteria: deterministic rule-based metrics measure properties with direct correspondences, while asset-specific vision-language rubrics capture semantic and perceptual qualities for which exact matching is misleading. Besides, we propose DrawAI-Flow, a two-stage agentic workflow in which a Parser Agent turns extracted elements evidence into an explicit reconstruction plan, and a Reconstruction Agent realizes the plan as executable graphics code through an iterative code-render-validate-revise loop. On DrawAI-Bench, we systematically evaluate thirteen models across five agent harnesses to study the effects of model capability, harness choice, and workflow design. The results show that reconstruction quality and costs vary substantially across model-harness configurations, while DrawAI-Flow consistently improves editable structure.

Related papers

• CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences [51.86576932800981]
  We introduce CV-Arena, an open benchmark designed to evaluate this capability at professional scales.<n>CV-Arena contains 12K high-resolution real-image instruction pairs spanning 16 instruction-based visual task types.<n>We develop CV-Agent, a lightweight agentic model that combines planning, editing, and verification.
  arXiv  Detail & Related papers  (2026-05-30T23:37:55Z)
• How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing [56.60465182650588]
  We introduce three-level interaction hierarchy that captures deictic grounding, morphological manipulation, and causal reasoning.<n>We propose a robust LMM-as-a-judge evaluation framework with task-specific metrics to enable scalable and fine-grained assessment.<n>We find that proprietary models exhibit early-stage visual instruction-following capabilities and consistently outperform open-source models.
  arXiv  Detail & Related papers  (2026-02-02T09:24:45Z)
• 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)
• Image-POSER: Reflective RL for Multi-Expert Image Generation and Editing [16.943575863059607]
  Image-POSER orchestrates a diverse registry of pretrained text-to-image and image-to-image experts.<n>It handles long-form prompts end-to-end through dynamic task decomposition.<n>It is consistently preferred in human evaluations.
  arXiv  Detail & Related papers  (2025-11-15T03:15:34Z)
• EditInfinity: Image Editing with Binary-Quantized Generative Models [64.05135380710749]
  We investigate the parameter-efficient adaptation of binary-quantized generative models for image editing.<n>Specifically, we propose EditInfinity, which adapts emphInfinity, a binary-quantized generative model, for image editing.<n>We propose an efficient yet effective image inversion mechanism that integrates text prompting rectification and image style preservation.
  arXiv  Detail & Related papers  (2025-10-23T05:06:24Z)
• Foundations and Models in Modern Computer Vision: Key Building Blocks in Landmark Architectures [34.542592986038265]
  This report analyzes the evolution of key design patterns in computer vision by examining six influential papers.<n>We review ResNet, which introduced residual connections to overcome the vanishing gradient problem.<n>We examine the Vision Transformer (ViT), which established a new paradigm by applying the Transformer architecture to sequences of image patches.
  arXiv  Detail & Related papers  (2025-07-31T09:08:11Z)
• Unpaired Deblurring via Decoupled Diffusion Model [55.21345354747609]
  We propose UID-Diff, a generative-diffusion-based model designed to enhance deblurring performance on unknown domains.<n>We employ two Q-Formers as structural features and blur patterns extractors separately. The features extracted will be used for the supervised deblurring task on synthetic data and the unsupervised blur-transfer task.<n>Experiments on real-world datasets demonstrate that UID-Diff outperforms existing state-of-the-art methods in blur removal and structural preservation.
  arXiv  Detail & Related papers  (2025-02-03T17:00:40Z)
• CART: Compositional Auto-Regressive Transformer for Image Generation [2.48490797934472]
  We propose a novel Auto-Regressive (AR) image generation approach that models images as hierarchical compositions of interpretable visual layers.<n>CART adds image details iteratively via semantically meaningful decompositions.<n>We show CART generates visually compelling results while enabling structured image manipulation.
  arXiv  Detail & Related papers  (2024-11-15T13:29:44Z)
• Zero-shot Composed Text-Image Retrieval [72.43790281036584]
  We consider the problem of composed image retrieval (CIR) It aims to train a model that can fuse multi-modal information, e.g., text and images, to accurately retrieve images that match the query, extending the user's expression ability.
  arXiv  Detail & Related papers  (2023-06-12T17:56:01Z)
• Toward a Controllable Disentanglement Network [22.968760397814993]
  This paper addresses two crucial problems of learning disentangled image representations, namely controlling the degree of disentanglement during image editing, and balancing the disentanglement strength and the reconstruction quality. By exploring the real-valued space of the soft target representation, we are able to synthesize novel images with the designated properties.
  arXiv  Detail & Related papers  (2020-01-22T16:54:07Z)

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.