用于高保真图像到图像翻译的 Hierarchy Flow
Hierarchy Flow For High-Fidelity Image-to-Image Translation
AI总结：
针对图像到图像翻译中的内容保真问题，论文提出基于分层耦合和对齐风格损失的流模型 Hierarchy Flow，在多类基准上达到最先进性能。
摘要：
图像到图像（I2I）翻译涵盖范围广泛的一系列任务。本文将该问题划分为三个层级：强保真翻译、正常保真翻译和弱保真翻译，用以表示原始图像内容被保留的程度。尽管现有方法在弱保真翻译中取得了良好性能，但它们在强保真和正常保真任务中都无法充分保留内容，例如 sim2real、风格迁移和低层视觉。本文提出 Hierarchy Flow，这是一种新颖的基于流的模型，旨在翻译过程中实现更好的内容保留。具体而言：1）我们首先揭示标准基于流的模型应用于 I2I 翻译时的缺陷；2）接着提出一种新设计，即用于可逆特征变换和多尺度建模的分层耦合，以构成 Hierarchy Flow；3）最后提出一种专用的对齐风格损失，以便在翻译过程中更好地权衡内容保留与风格化。在大量 I2I 翻译基准上的广泛实验表明，本方法达到了最先进性能，并在强保真和正常保真任务中均具有令人信服的优势。代码和模型将发布于 https://github.com/WeichenFan/HierarchyFlow。
英文摘要：
Image-to-image (I2I) translation comprises a wide spectrum of tasks. Here we divide this problem into three levels: strong-fidelity translation, normal-fidelity translation, and weak-fidelity translation, indicating the extent to which the content of the original image is preserved. Although existing methods achieve good performance in weak-fidelity translation, they fail to fully preserve the content in both strong- and normal-fidelity tasks, e.g. sim2real, style transfer and low-level vision. In this work, we propose Hierarchy Flow, a novel flow-based model to achieve better content preservation during translation. Specifically, 1) we first unveil the drawbacks of standard flow-based models when applied to I2I translation. 2) Next, we propose a new design, namely hierarchical coupling for reversible feature transformation and multi-scale modeling, to constitute Hierarchy Flow. 3) Finally, we present a dedicated aligned-style loss for a better trade-off between content preservation and stylization during translation. Extensive experiments on a wide range of I2I translation benchmarks demonstrate that our approach achieves state-of-the-art performance, with convincing advantages in both strong- and normal-fidelity tasks. Code and models will be at https://github.com/WeichenFan/HierarchyFlow.
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。
