Moodifier：MLLM增强的情感驱动图像编辑
Moodifier: MLLM-Enhanced Emotion-Driven Image Editing
AI总结：
本文提出Moodifier情感驱动图像编辑系统，通过MoodArchive数据集、MoodifyCLIP模型与多模态大语言模型协同，在保持内容完整性的同时实现精确情感转换，并在多领域实验中优于现有方法。
摘要：
将情感与视觉内容相连接以实现情感驱动的图像编辑，在创意产业中具有巨大潜力，然而由于情感的抽象性及其在不同语境下的多样表现，精确操控仍然具有挑战性。我们通过一个由三个互补组件构成的集成方法来应对这一挑战。首先，我们引入了MoodArchive，这是一个包含800万张以上图像的数据集，具有由LLaVA生成的详细分层情感标注，并经过人类评估者的部分验证。其次，我们开发了MoodifyCLIP，这是一个在MoodArchive上微调的视觉-语言模型，用于将抽象情感转化为具体的视觉属性。第三，我们提出了Moodifier，这是一个免训练编辑模型，利用MoodifyCLIP和多模态大语言模型（MLLMs）实现精确的情感转换，同时保持内容完整性。我们的系统适用于角色表情、时尚设计、珠宝和家居装饰等多种领域，使创作者能够快速可视化情感变化，同时保持身份和结构。大量实验评估表明，Moodifier在情感准确性和内容保持方面均优于现有方法，提供了符合语境的编辑效果。通过将抽象情感与具体视觉变化联系起来，我们的解决方案为现实应用中的情感内容创作开启了新的可能性。我们将在录用后公开发布MoodArchive数据集、MoodifyCLIP模型，并提供Moodifier代码和演示。
英文摘要：
Bridging emotions and visual content for emotion-driven image editing holds great potential in creative industries, yet precise manipulation remains challenging due to the abstract nature of emotions and their varied manifestations across different contexts. We tackle this challenge with an integrated approach consisting of three complementary components. First, we introduce MoodArchive, an 8M+ image dataset with detailed hierarchical emotional annotations generated by LLaVA and partially validated by human evaluators. Second, we develop MoodifyCLIP, a vision-language model fine-tuned on MoodArchive to translate abstract emotions into specific visual attributes. Third, we propose Moodifier, a training-free editing model leveraging MoodifyCLIP and multimodal large language models (MLLMs) to enable precise emotional transformations while preserving content integrity. Our system works across diverse domains such as character expressions, fashion design, jewelry, and home décor, enabling creators to quickly visualize emotional variations while preserving identity and structure. Extensive experimental evaluations show that Moodifier outperforms existing methods in both emotional accuracy and content preservation, providing contextually appropriate edits. By linking abstract emotions to concrete visual changes, our solution unlocks new possibilities for emotional content creation in real-world applications. We will release the MoodArchive dataset, MoodifyCLIP model, and make the Moodifier code and demo publicly available upon acceptance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
