From Evaluation to Evolution: Benchmarking Image Editing and Evolving Image Models
中文摘要
WeGenEditBench 引入 2,740 个实例,通过细分评估识别图像编辑的局部失败,推动模型精准优化与演进。
English Summary
WeGenEditBench introduces 2,740 instances to identify local image editing failures, translating them into actionable priorities for model improvement and evolution.
arXiv:2610.41210v1 Announce Type: cross Abstract: Real-world image editing requires coordinating multiple visual transformations with content preservation and reference constraints, yet aggregate scores can readily obscure unmet local requirements. Effective evaluation must therefore identify local failures and translate them into priorities for subsequent model improvement. We introduce WeGenEditBench, comprising 2,740 evaluation instances and 148 task types across single-image, text-intensive, and multi-reference editing. Pre-generated checklists shared across models decompose each request into atomic requirements; item-level deductions and visual evidence are established first and then summarized into scores for edit execution, preservation, visual quality, and task-specific correctness. To support the experience-acquisition component of recursive self-improvement (RSI), we develop WeGenEvoStudio, a unified multi-agent harness for RSI-oriented learning that integrates model-conditioned failure diagnosis, retrieval-grounded data construction, supervised adaptation, and re-evaluation. Among 15 evaluated configurations, GPT-Image-2 leads single-image editing with an Overall score o…