论文标题
用斑块空间神经转换融合的一声细节修饰
One-shot Detail Retouching with Patch Space Neural Transformation Blending
论文作者
论文摘要
对于新手用户来说，照片修饰是一项艰巨的任务，因为它需要专家知识和高级工具。摄影师经常花费大量时间来产生高质量的修饰照片，并带有复杂的细节。在本文中，我们介绍了一种基于单次学习的技术，以自动修饰基于一对前后示例图像的输入图像的细节。我们的方法提供了准确且可推广的详细信息编辑转移到新图像。我们通过提出图像图的新表示形式来实现这些目标。具体而言，我们建议在斑块空间中基于神经场的转换混合，以定义每个频带的贴片变换。用锚点转换和相关的权重以及时空光谱的局部贴片对地图的参数化，使我们能够在保持可概括的同时很好地捕获细节。我们在已知的地面真相过滤器和艺术家修饰的编辑中评估我们的技术。我们的方法准确地传递了复杂的细节修饰编辑。
Photo retouching is a difficult task for novice users as it requires expert knowledge and advanced tools. Photographers often spend a great deal of time generating high-quality retouched photos with intricate details. In this paper, we introduce a one-shot learning based technique to automatically retouch details of an input image based on just a single pair of before and after example images. Our approach provides accurate and generalizable detail edit transfer to new images. We achieve these by proposing a new representation for image to image maps. Specifically, we propose neural field based transformation blending in the patch space for defining patch to patch transformations for each frequency band. This parametrization of the map with anchor transformations and associated weights, and spatio-spectral localized patches, allows us to capture details well while staying generalizable. We evaluate our technique both on known ground truth filters and artist retouching edits. Our method accurately transfers complex detail retouching edits.
