PREIM3D：从单张图像进行 3D 一致的精确图像属性编辑
PREIM3D: 3D Consistent Precise Image Attribute Editing from a Single Image
AI总结：
本文提出 PREIM3D，通过共享编码器、交替训练、多视角身份损失及反演流形编辑，实现单图 3D 感知属性编辑的高一致性与精确性。
摘要：
本文研究具有广泛实际应用的 3D 感知图像属性编辑问题。近期方法通过训练一个共享编码器，将图像映射到 3D 生成器的潜空间，或者通过逐图像的潜码优化来解决该问题，随后在潜空间中编辑图像。尽管这些方法在输入视角附近取得了可观结果，但它们仍存在生成图像在大相机姿态下 3D 不一致，以及图像属性编辑不精确的问题，例如在编辑过程中影响未指定的属性。为实现更高效的图像反演，我们为所有图像训练一个共享编码器。为缓解大相机姿态下的 3D 不一致问题，我们提出两种新方法：交替训练方案和多视角身份损失，用于保持 3D 一致性和主体身份。针对不精确的图像编辑，我们将该问题归因于真实图像潜空间与生成图像潜空间之间的差距。我们比较了 GAN 模型的潜空间和反演流形，并证明在反演流形中进行编辑能够在定量和定性评估中取得更好结果。大量实验表明，与先前工作相比，我们的方法生成更具 3D 一致性的图像，并实现更精确的图像编辑。源代码和预训练模型可在项目页面获取：https://mybabyyh.github.io/Preim3D/
英文摘要：
We study the 3D-aware image attribute editing problem in this paper, which has wide applications in practice. Recent methods solved the problem by training a shared encoder to map images into a 3D generator's latent space or by per-image latent code optimization and then edited images in the latent space. Despite their promising results near the input view, they still suffer from the 3D inconsistency of produced images at large camera poses and imprecise image attribute editing, like affecting unspecified attributes during editing. For more efficient image inversion, we train a shared encoder for all images. To alleviate 3D inconsistency at large camera poses, we propose two novel methods, an alternating training scheme and a multi-view identity loss, to maintain 3D consistency and subject identity. As for imprecise image editing, we attribute the problem to the gap between the latent space of real images and that of generated images. We compare the latent space and inversion manifold of GAN models and demonstrate that editing in the inversion manifold can achieve better results in both quantitative and qualitative evaluations. Extensive experiments show that our method produces more 3D consistent images and achieves more precise image editing than previous work. Source code and pretrained models can be found on our project page: https://mybabyyh.github.io/Preim3D/
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。
