arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.11262cs.CVeess.IV
收藏

低分辨率条件下的图像到图像转换

Image-to-Image Translation with Low Resolution Conditioning

Université Laval(拉瓦尔大学);Mila(米拉研究所)

Mohamed Abderrahmen Abid, Ihsen Hedhli, Jean-François Lalonde, Christian Gagne

摘要:

大多数图像到图像翻译方法专注于学习跨域的映射,假设图像共享内容(例如,姿势),但是具有它们自己的特定于域的信息,称为样式。当以目标图像为条件时,这种方法旨在提取目标的风格并将其与源图像的内容相结合。在这项工作中,我们考虑的情况下,目标图像具有非常低的分辨率。更具体地说,我们的方法的目的是从高分辨率(HR)源图像的精细细节,以适应粗糙,低分辨率(LR)的图像表示的目标。因此,我们生成HR图像,这些图像共享HR和LR输入的特征。这与以前的方法不同,以前的方法专注于将给定的图像风格翻译成目标内容,我们的翻译方法能够同时模仿风格并合并LR目标的结构信息。我们的方法依赖于训练生成模型来产生HR目标图像,该HR目标图像1)共享相关联的源图像的独特信息; 2)在缩小时正确地匹配LR目标图像。我们在CelebA-HQ和AFHQ数据集上验证了我们的方法,展示了视觉质量,多样性和覆盖率方面的改进。定性和定量的结果表明,当处理域内图像平移时,与Stargan-v2等最先进的方法相比,我们的方法生成了更真实的样本

英文摘要:

Most image-to-image translation methods focus on learning mappings across domains with the assumption that images share content (e.g., pose) but have their own domain-specific information known as style. When conditioned on a target image, such methods aim to extract the style of the target and combine it with the content of the source image. In this work, we consider the scenario where the target image has a very low resolution. More specifically, our approach aims at transferring fine details from a high resolution (HR) source image to fit a coarse, low resolution (LR) image representation of the target. We therefore generate HR images that share features from both HR and LR inputs. This differs from previous methods that focus on translating a given image style into a target content, our translation approach being able to simultaneously imitate the style and merge the structural information of the LR target. Our approach relies on training the generative model to produce HR target images that both 1) share distinctive information of the associated source image; 2) correctly match the LR target image when downscaled. We validate our method on the CelebA-HQ and AFHQ datasets by demonstrating improvements in terms of visual quality, diversity and coverage. Qualitative and quantitative results show that when dealing with intra-domain image translation, our method generates more realistic samples compared to state-of-the-art methods such as Stargan-v2

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。

↑