arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.01217cs.CVcs.GR
收藏

基于块空间神经变换混合的一次性细节修饰

One-shot Detail Retouching with Patch Space Neural Transformation Blending

University of Cambridge(剑桥大学)

Fazilet Gokbudak, Cengiz Oztireli

AI总结:

本文提出一种基于一次性学习的细节修饰迁移方法,通过在块空间中引入神经场变换混合表示,仅用一对修饰前后示例即可将复杂细节编辑准确泛化到新图像。

摘要:

照片修饰对新手用户而言是一项困难的任务,因为它需要专业知识和高级工具。摄影师通常花费大量时间生成具有复杂细节的高质量修饰照片。在本文中,我们提出一种基于一次性学习的技术,仅根据一对修饰前后的示例图像,即可自动修饰输入图像的细节。我们的方法能够将细节编辑准确且可泛化地迁移到新图像上。为此,我们提出了一种新的图像到图像映射表示方法。具体来说,我们提出了在块空间中基于神经场的变换混合,用于为每个频带定义块到块的变换。这种通过锚变换及其相关权重以及空间-频谱局部化块对映射进行参数化的方式,使我们能够在保持泛化能力的同时很好地捕捉细节。我们在已知真值滤波器和艺术家修饰编辑上评估了我们的技术。我们的方法能够准确地迁移复杂的细节修饰编辑。

英文摘要:

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.

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。

↑