研究人员推出了MPIE-Bench，这是一个旨在评估文本到图像和编辑模型准确描绘多人交互能力的新基准。该基准包含2,500个视频挖掘的编辑三元组，侧重于解剖学上的合理性和交互准确性，解决了肢体融合和身体穿透等常见失败问题。MPIE-Eval，一个新的评估指标，使用网格重建对接触时间几何进行评分，表明当前模型在解剖学和交互方面同时表现出色存在困难，在通过视觉语言模型评估时，其表现通常优于人类判断。 AI
影响 该基准可以推动AI生成逼真多人场景能力的改进，影响创意工具和虚拟环境。
排序理由 该集群描述了一个新的AI模型学术基准和评估指标。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Text-to-image and personalized editing models now synthesize high-fidelity single-subject images with ease. Yet placing multiple named people into shared contact actions such as embrace, carry, or grapple still exposes major failures: fused limbs, invented extremities, and interp…
Text-to-image and personalized editing models now synthesize high-fidelity single-subject images with ease. Yet placing multiple named people into shared contact actions such as embrace, carry, or grapple still exposes major failures: fused limbs, invented extremities, and interp…
arXiv:2607.27616v1 Announce Type: new Abstract: Text-to-image and personalized editing models now synthesize high-fidelity single-subject images with ease. Yet placing multiple named people into shared contact actions such as embrace, carry, or grapple still exposes major failure…