MICo-150K：推进多图像合成的综合数据集
MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition
该数据集为多图像合成任务提供了大规模训练数据和标准化评测基准，其提出的 Weighted-Ref-VIEScore 指标和 De&Re 子集可用于评估和提升模型在多参考输入下的身份一致性与组合能力。
原文依据 we construct MICo-Bench with 100 cases per task and 300 challenging De&Re cases
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在可控图像生成中，从多个参考输入合成连贯且一致的图像，即多图像合成（MICo），仍然是一个具有挑战性的问题，部分原因在于缺乏高质量训练数据。为弥补这一空白，我们对MICo进行了系统研究，将其分为7个代表性任务，并整理了大量高质量源图像，构建了多样化的MICo提示。利用强大的专有模型，我们合成了大量均衡的合成图像，随后通过人工参与过滤和精炼，得到了MICo-150K，这是一个具有身份一致性的综合MICo数据集。我们进一步构建了分解与重组（De&Re）子集，其中11K真实世界复杂图像被分解为组件并重组，从而同时支持真实和合成组合。为实现全面评估，我们构建了MICo-Bench，每个任务100个案例，以及300个具有挑战性的De&Re案例，并进一步引入了一种新指标Weighted-Ref-VIEScore，专门用于MICo评估。最后，我们在MICo-150K上微调了多个模型，并在MICo-Bench上评估它们。结果表明，MICo-150K有效地赋予了不具备MICo能力的模型该能力，并进一步增强了已有技能的模型。值得注意的是，从Qwen-Image-Edit微调得到的Qwen-MICo在三图像合成上达到了与Qwen-Image-2509相当的水平，同时支持后者所不具备的任意多图像输入。我们的数据集和基准将成为推进MICo研究的宝贵资源。
英文原文摘要 1599 字符
In controllable image generation, synthesizing coherent and consistent images from multiple reference inputs, i.e., **Multi-Image Composition** (MICo), remains a challenging problem, partly hindered by the lack of high-quality training data.To bridge this gap, we conduct a systematic study of MICo, categorizing it into 7 representative tasks and curate a large-scale collection of high-quality source images and construct diverse MICo prompts.Leveraging powerful proprietary models, we synthesize a rich amount of balanced composite images, followed by human-in-the-loop filtering and refinement, resulting in **MICo-150K**, a comprehensive dataset for MICo with identity consistency.We further build a Decomposition-and-Recomposition (**De&Re**) subset, where 11K real-world complex images are decomposed into components and recomposed, enabling both real and synthetic compositions.To enable comprehensive evaluation, we construct **MICo-Bench** with 100 cases per task and 300 challenging De&Re cases, and further introduce a new metric, **Weighted-Ref-VIEScore**, specifically tailored for MICo evaluation.Finally, we fine-tune multiple models on**MICo-150K** and evaluate them on **MICo-Bench**. The results show that MICo-150K effectively equips models without MICo capability and further enhances those with existing skills.Notably, **Qwen-MICo**, fine-tuned from Qwen-Image-Edit, matches **Qwen-Image-2509** in 3-image composition while supporting arbitrary multi-image inputs beyond the latter's limitation.Our dataset and benchmark will be valuable resources for advancing MICo research.