一种用于解耦可控图像编辑的紧凑语义潜在空间
A Compact and Semantic Latent Space for Disentangled and Controllable Image Editing
AI总结：
针对现有GAN图像编辑方法解耦性不足的问题，提出一种基于主成分分析压缩潜在空间的自动编码器，重构StyleGAN潜在空间以实现属性解耦编辑，训练快、解耦效果优且保持图像身份保真度，架构易实现。
摘要：
生成模型尤其是生成对抗网络（GANs）领域的最新进展，为可控图像编辑带来了实质性突破，与深度学习前的时代相比尤为显著。尽管这类方法具备对图像进行逼真修改的强大能力，但往往缺乏解耦性（即独立编辑不同属性的能力）等特性。本文提出一种自动编码器，对StyleGAN的潜在空间进行重构，使我们想要编辑的每个属性都对应新潜在空间的一个轴，且这些潜在轴相互去相关，以促进解耦效果。我们在经主成分分析（Principal Component Analysis）压缩的潜在空间版本中开展研究，这意味着自动编码器的参数复杂度得以降低，训练时间较短（约45分钟）。定性与定量结果均验证了本文方法的编辑能力：其解耦性优于现有对比方法，同时能保持原始图像的身份保真度。我们的自动编码器架构简单直接，便于实现。
英文摘要：
Recent advances in the field of generative models and in particular generative adversarial networks (GANs) have lead to substantial progress for controlled image editing, especially compared with the pre-deep learning era. Despite their powerful ability to apply realistic modifications to an image, these methods often lack properties like disentanglement (the capacity to edit attributes independently). In this paper, we propose an auto-encoder which re-organizes the latent space of StyleGAN, so that each attribute which we wish to edit corresponds to an axis of the new latent space, and furthermore that the latent axes are decorrelated, encouraging disentanglement. We work in a compressed version of the latent space, using Principal Component Analysis, meaning that the parameter complexity of our autoencoder is reduced, leading to short training times ($\sim$ 45 mins). Qualitative and quantitative results demonstrate the editing capabilities of our approach, with greater disentanglement than competing methods, while maintaining fidelity to the original image with respect to identity. Our autoencoder architecture simple and straightforward, facilitating implementation.
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。
