For semantic-guided cross-view image translation, it is crucial to learn where to sample pixels from the source view image and where to reallocate them guided by the target view semantic map, especially when there is little overlap or drastic view difference between the source and target images. Hence, one not only needs to encode the long-range dependencies among pixels in both the source view image and target view the semantic map but also needs to translate these learned dependencies. To this end, we propose a novel generative adversarial network, PI-Trans, which mainly consists of a novel Parallel-ConvMLP module and an Implicit Transformation module at multiple semantic levels. Extensive experimental results show that the proposed PI-Trans achieves the best qualitative and quantitative performance by a large margin compared to the state-of-the-art methods on two challenging datasets. The code will be made available at https://github.com/Amazingren/PI-Trans.

中文翻译：

---

PI-Trans：用于跨视图图像翻译的 Parallel-ConvMLP 和基于隐式变换的 GAN

对于语义引导的跨视图图像翻译，了解从源视图图像中采样像素的位置以及在目标视图语义图的引导下重新分配像素的位置至关重要，尤其是当源视图之间几乎没有重叠或剧烈的视图差异时和目标图像。因此，不仅需要对源视图图像和目标视图中像素之间的长程依赖关系进行编码，还需要翻译这些学习到的依赖关系。为此，我们提出了一种新颖的生成对抗网络 PI-Trans，它主要由一个新颖的 Parallel-ConvMLP 模块和多个语义级别的隐式转换模块组成。广泛的实验结果表明，与两个具有挑战性的数据集上的最新方法相比，所提出的 PI-Trans 实现了最佳的定性和定量性能。该代码将在 https://github.com/Amazingren/PI-Trans 上提供。