论文标题
Styleres：使用StyleGan进行真实图像编辑的残差
StyleRes: Transforming the Residuals for Real Image Editing with StyleGAN
论文作者
论文摘要
我们提出了一个新型的图像反转框架和一个训练管道，以实现具有高质量属性编辑的高保真图像反转。将真实图像倒入StyleGan的潜在空间是一个广泛研究的问题，但是图像重建保真度和图像编辑质量之间的权衡仍然是一个开放的挑战。低率潜在空间的表现力能力有限，以实现高保真重建。另一方面，高速潜在的潜在空间导致编辑质量的降级。在这项工作中，为了实现高保真倒置，我们在较高的潜在代码中学习了剩余的特征，而潜在的代码无法编码。这可以在重建中保存图像细节。为了获得高质量的编辑，我们学习了如何改变对潜在代码中的操纵的残差特征。我们训练框架以提取剩余特征，并通过新的建筑管道和循环一致性损失来改变它们。我们运行广泛的实验，并将我们的方法与最新的反转方法进行比较。定性指标和视觉比较显示出重大改进。代码：https：//github.com/hamzapehlivan/styleres
We present a novel image inversion framework and a training pipeline to achieve high-fidelity image inversion with high-quality attribute editing. Inverting real images into StyleGAN's latent space is an extensively studied problem, yet the trade-off between the image reconstruction fidelity and image editing quality remains an open challenge. The low-rate latent spaces are limited in their expressiveness power for high-fidelity reconstruction. On the other hand, high-rate latent spaces result in degradation in editing quality. In this work, to achieve high-fidelity inversion, we learn residual features in higher latent codes that lower latent codes were not able to encode. This enables preserving image details in reconstruction. To achieve high-quality editing, we learn how to transform the residual features for adapting to manipulations in latent codes. We train the framework to extract residual features and transform them via a novel architecture pipeline and cycle consistency losses. We run extensive experiments and compare our method with state-of-the-art inversion methods. Qualitative metrics and visual comparisons show significant improvements. Code: https://github.com/hamzapehlivan/StyleRes
