HairDiffusion：基于潜在扩散的生动多色头发编辑
HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion
AI总结：
本文提出HairDiffusion，利用LDMs和Multi-stage Hairstyle Blend分离头发颜色与发型控制，结合warping模块与微调CLIP，实现高质量多色头发编辑并保留面部属性。
摘要：
头发编辑是一项关键的图像合成任务，旨在通过文本描述或参考图像编辑头发颜色和发型，同时保留无关属性（如身份、背景、衣物）。许多现有方法基于StyleGAN来解决此任务。然而，由于StyleGAN的空间分布有限，它在多色头发编辑和面部保留方面存在困难。考虑到扩散模型的进展，我们利用Latent Diffusion Models (LDMs)进行发型编辑。我们的方法引入了Multi-stage Hairstyle Blend (MHB)，在扩散潜在空间中有效地分离了对头发颜色和发型的控制。此外，我们训练了一个warping模块来将头发颜色与目标区域对齐。为了进一步增强多色发型编辑，我们使用多色发型数据集微调了CLIP模型。我们的方法不仅解决了多色发型的复杂性，还解决了在扩散编辑过程中保留原始颜色的挑战。大量实验展示了我们的方法在编辑多色发型以及在给定文本描述和参考图像时保留面部属性方面的优越性。
英文摘要：
Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images.
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。
