Color Bind: 探索文本到图像模型中的颜色感知
Color Bind: Exploring Color Perception in Text-to-Image Models
AI总结：
本文提出了一种专门的图像编辑技术，用于解决多对象提示中颜色属性的语义对齐问题，并在多种指标上提升了性能。
摘要：
文本到图像生成最近取得了显著的成功，使用户能够通过文本创建高质量的图像。然而，当前的方法在捕捉复杂多对象提示中所传达的精确语义方面面临挑战。因此，许多工作试图减轻这种语义错位，通常通过推理时间的方案来修改去噪网络的注意力层。然而，先前的工作大多使用粗略的指标，如文本和图像CLIP嵌入之间的余弦相似度，或人工评估，这些在更大规模上难以进行。在本工作中，我们对颜色进行了案例研究——颜色是文本提示中与对象常见关联的基本属性，为严格评估提供了丰富的测试环境。我们的分析揭示了预训练模型在生成忠实反映多种颜色属性的图像方面远不如单色提示，并且既没有推理时间技术，也没有现有编辑方法能够可靠地解决这些语义错位。因此，我们引入了一种专门的图像编辑技术，以缓解包含多种颜色的提示中的多对象语义对齐问题。我们证明了我们的方法在各种指标上显著提高了性能，考虑到由各种文本到图像扩散技术生成的图像。
英文摘要：
Text-to-image generation has recently seen remarkable success, granting users with the ability to create high-quality images through the use of text. However, contemporary methods face challenges in capturing the precise semantics conveyed by complex multi-object prompts. Consequently, many works have sought to mitigate such semantic misalignments, typically via inference-time schemes that modify the attention layers of the denoising networks. However, prior work has mostly utilized coarse metrics, such as the cosine similarity between text and image CLIP embeddings, or human evaluations, which are challenging to conduct on a larger-scale. In this work, we perform a case study on colors -- a fundamental attribute commonly associated with objects in text prompts, which offer a rich test bed for rigorous evaluation. Our analysis reveals that pretrained models struggle to generate images that faithfully reflect multiple color attributes-far more so than with single-color prompts-and that neither inference-time techniques nor existing editing methods reliably resolve these semantic misalignments. Accordingly, we introduce a dedicated image editing technique, mitigating the issue of multi-object semantic alignment for prompts containing multiple colors. We demonstrate that our approach significantly boosts performance over a wide range of metrics, considering images generated by various text-to-image diffusion-based techniques.
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。
