Recent studies show strong generative performance in domain translation especially by using transfer learning techniques on the unconditional generator. However, the control between different domain features using a single model is still challenging. Existing methods often require additional models, which is computationally demanding and leads to unsatisfactory visual quality. In addition, they have restricted control steps, which prevents a smooth transition. In this paper, we propose a new approach for high-quality domain translation with better controllability. The key idea is to preserve source features within a disentangled subspace of a target feature space. This allows our method to smoothly control the degree to which it preserves source features while generating images from an entirely new domain using only a single model. Our extensive experiments show that the proposed method can produce more consistent and realistic images than previous works and maintain precise controllability over different levels of transformation. The code is available at https://github.com/LeeDongYeun/FixNoise.

翻译：最近的研究表明，尤其在无条件生成器上运用迁移学习技术时，域转换展现出强大的生成性能。然而，使用单一模型在不同域特征之间进行控制仍颇具挑战。现有方法往往需要额外的模型，这不仅计算量大，还会导致令人不满意的视觉质量。此外，它们具有受限的控制步长，阻碍了平滑的过渡。在本文中，我们提出了一种新方法，用于实现高质量且具更优可控性的域转换。其关键思想是在目标特征空间的解耦子空间中保留源域特征。这使得我们的方法能够仅使用单一模型平滑地控制保留源域特征的程度，同时从全新的域生成图像。我们大量的实验表明，与先前的工作相比，所提出的方法能生成更一致且逼真的图像，并在不同变换程度上保持精确的可控性。代码见 https://github.com/LeeDongYeun/FixNoise。