Chimera：基于部件概念化的组合式图像生成
Chimera: Compositional Image Generation using Part-based Concepting
AI总结：
针对现有个性化图像生成模型缺乏多源部件组合显式控制的问题，提出Chimera模型，通过构建语义原子数据集、训练带部件条件引导的扩散先验模型实现文本指导的部件组合生成，还提出PartEval评估指标，性能显著优于基线。
摘要：
个性化图像生成模型非常擅长根据文本或单张图像合成图像，但它们缺乏在无需用户指定掩码或标注的情况下，从多张源图像的特定部件组合出物体的显式控制能力。为解决这一问题，我们提出Chimera，这是一种个性化图像生成模型，可根据文本指令结合不同源图像的指定部件生成新物体。为训练我们的模型，我们首先基于由464个独特的（部件，主体）对（我们称之为语义原子）构建的分类体系构建了一个数据集。基于此，我们生成了3.7万条提示词，并用高保真文本到图像模型合成了对应的图像。我们训练了一个带有部件条件引导的定制扩散先验模型，该模型引导图像条件特征以同时保证语义一致性和空间布局。我们还提出了一个客观指标PartEval，用于评估生成流程的保真度和组合准确性。人工评估以及我们提出的指标显示，Chimera在部件对齐和组合准确性方面优于其他基线14%，在视觉质量方面优于21%。
英文摘要：
Personalized image generative models are highly proficient at synthesizing images from text or a single image, yet they lack explicit control for composing objects from specific parts of multiple source images without user specified masks or annotations. To address this, we introduce Chimera, a personalized image generation model that generates novel objects by combining specified parts from different source images according to textual instructions. To train our model, we first construct a dataset from a taxonomy built on 464 unique (part, subject) pairs, which we term semantic atoms. From this, we generate 37k prompts and synthesize the corresponding images with a high-fidelity text-to-image model. We train a custom diffusion prior model with part-conditional guidance, which steers the image-conditioning features to enforce both semantic identity and spatial layout. We also introduce an objective metric PartEval to assess the fidelity and compositional accuracy of generation pipelines. Human evaluations and our proposed metric show that Chimera outperforms other baselines by 14% in part alignment and compositional accuracy and 21% in visual quality.
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。
