Image-to-image (i2i) networks struggle to capture local changes because they do not affect the global scene structure. For example, translating from highway scenes to offroad, i2i networks easily focus on global color features but ignore obvious traits for humans like the absence of lane markings. In this paper, we leverage human knowledge about spatial domain characteristics which we refer to as 'local domains' and demonstrate its benefit for image-to-image translation. Relying on a simple geometrical guidance, we train a patch-based GAN on few source data and hallucinate a new unseen domain which subsequently eases transfer learning to target. We experiment on three tasks ranging from unstructured environments to adverse weather. Our comprehensive evaluation setting shows we are able to generate realistic translations, with minimal priors, and training only on a few images. Furthermore, when trained on our translations images we show that all tested proxy tasks are significantly improved, without ever seeing target domain at training.
翻译:图像到图像 (i2i) 网络努力捕捉本地变化, 因为它们不会影响全球场景结构。 例如, 从高速公路场景到路外的转换, i2i 网络很容易关注全球色彩特征, 但忽视人类的明显特征, 例如没有车道标记。 在本文中, 我们利用人类对空间域特性的知识, 我们称之为“ 本地域 ”, 并展示其对于图像到图像翻译的好处。 依靠简单的几何制导, 我们训练了一个基于补丁的 GAN, 以少数源数据为主, 并给一个新的未知域带来幻觉, 从而方便了将学习转移至目标。 我们在三个任务上进行实验, 从无结构的环境到恶劣的天气。 我们的全面评估显示, 我们能产生现实的翻译, 使用最少的先前版本, 并且只对少数图像进行培训 。 此外, 当我们接受翻译图像培训时, 我们显示所有测试过的代理任务都大大改进了, 没有在培训中看到目标域 。