论文标题
没有域名的高分辨率白天翻译
High-Resolution Daytime Translation Without Domain Labels
论文作者
论文摘要
在高分辨率照片中进行建模白天的变化，例如，在白天，夜晚或黎明的典型照明下重新呈现相同的场景是一项具有挑战性的图像操纵任务。我们介绍了此任务的高分辨率白天翻译（HIDT）模型。 HIDT结合了生成图像到图像模型和新的UPS采样方案，该方案允许以高分辨率应用图像翻译。该模型在常用的GAN指标和人类评估方面展示了竞争性结果。重要的是，这种良好的表现是由于在没有白天标签的静态景观图像的数据集上进行了培训。我们的结果可在https://saic-mdal.github.io/hidt/上获得。
Modeling daytime changes in high resolution photographs, e.g., re-rendering the same scene under different illuminations typical for day, night, or dawn, is a challenging image manipulation task. We present the high-resolution daytime translation (HiDT) model for this task. HiDT combines a generative image-to-image model and a new upsampling scheme that allows to apply image translation at high resolution. The model demonstrates competitive results in terms of both commonly used GAN metrics and human evaluation. Importantly, this good performance comes as a result of training on a dataset of still landscape images with no daytime labels available. Our results are available at https://saic-mdal.github.io/HiDT/.
