基于解耦隐向量的图像到图像转换用于人脸编辑
Image-to-Image Translation with Disentangled Latent Vectors for Face Editing
AI总结：
提出一种基于解耦隐向量的图像到图像转换框架，通过隐空间分解和正交约束学习解耦属性方向，结合注意力跳跃连接的编码器-解码器架构，显著提升了人脸属性编辑的精确性与保真度。
摘要：
我们提出了一种用于人脸属性编辑的图像到图像转换框架，具有解耦的可解释隐方向。人脸属性编辑任务面临以下挑战：在可控强度下进行目标属性编辑，以及在属性表示中实现解耦，从而在编辑时保留其他属性。为达成此目标，受固定预训练 GAN 的隐空间分解工作启发，我们通过隐空间分解设计属性编辑，并为每个属性学习一个与其他方向正交的线性方向。我们使用正交约束和解耦损失来训练这些方向。为了将图像投影到语义组织的隐空间中，我们设置了带有基于注意力的跳跃连接的编码器-解码器架构。我们与之前的图像转换算法和预训练 GAN 编辑工作进行了广泛比较。大量实验表明，我们的方法显著优于现有技术。
英文摘要：
We propose an image-to-image translation framework for facial attribute editing with disentangled interpretable latent directions. Facial attribute editing task faces the challenges of targeted attribute editing with controllable strength and disentanglement in the representations of attributes to preserve the other attributes during edits. For this goal, inspired by the latent space factorization works of fixed pretrained GANs, we design the attribute editing by latent space factorization, and for each attribute, we learn a linear direction that is orthogonal to the others. We train these directions with orthogonality constraints and disentanglement losses. To project images to semantically organized latent spaces, we set an encoder-decoder architecture with attention-based skip connections. We extensively compare with previous image translation algorithms and editing with pretrained GAN works. Our extensive experiments show that our method significantly improves over the state-of-the-arts.
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。
