从生成对中学习特征保留的人像编辑
Learning Feature-Preserving Portrait Editing from Generated Pairs
AI总结：
本文提出一种基于自动生成配对数据的训练方法，利用Multi-Conditioned Diffusion Model和推理时的编辑掩码引导，在实现高质量人像编辑的同时有效保留主体特征。
摘要：
由于难以保留身份等主体特征，人像编辑对现有技术而言极具挑战。本文提出一种基于训练的方法，利用自动生成的配对数据来学习所需的编辑，同时确保未改变的主体特征得以保留。具体而言，我们设计了一种数据生成流程，以低成本为所需编辑创建高质量的训练对。基于这些训练对，我们引入了Multi-Conditioned Diffusion Model，以有效学习编辑方向并保留主体特征。在推理阶段，我们的模型生成准确的编辑掩码，引导推理过程进一步保留详细的主体特征。在服装编辑和卡通表情编辑上的实验表明，我们的方法在定量和定性上均达到了state-of-the-art的质量。
英文摘要：
Portrait editing is challenging for existing techniques due to difficulties in preserving subject features like identity. In this paper, we propose a training-based method leveraging auto-generated paired data to learn desired editing while ensuring the preservation of unchanged subject features. Specifically, we design a data generation process to create reasonably good training pairs for desired editing at low cost. Based on these pairs, we introduce a Multi-Conditioned Diffusion Model to effectively learn the editing direction and preserve subject features. During inference, our model produces accurate editing mask that can guide the inference process to further preserve detailed subject features. Experiments on costume editing and cartoon expression editing show that our method achieves state-of-the-art quality, quantitatively and qualitatively.
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。
