arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.03382cs.CV
收藏

图像修补的关键:结构和纹理齐头并进

Keys to Better Image Inpainting: Structure and Texture Go Hand in Hand

University of Oregon(俄勒冈大学);Salesforce Research(赛富时研究院);Picsart AI Research (PAIR)(Picsart人工智能研究院);Adobe Inc.(奥多比公司)

Jitesh Jain, Yuqian Zhou, Ning Yu, Humphrey Shi

摘要:

深度图像修补随着图像生成和处理算法的最新进展而取得了令人印象深刻的进展。我们认为,修复算法的性能可以更好地判断所产生的结构和纹理。结构是指生成的物体边界或洞内新颖的几何结构,而纹理是指高频细节,特别是填充在结构区域内的人造重复图案。我们认为,更好的结构通常是从基于GAN的粗到细生成器网络中获得的,而现在的重复模式可以使用最先进的高频快速傅立叶卷积层更好地建模。在本文中,我们提出了一种新的修复网络结合这两种设计的优点。因此,我们的模型实现了卓越的视觉质量,以匹配使用单个网络的结构生成和重复纹理合成的最新性能。大量的实验证明了该方法的有效性,并进一步强调了影响图像修补质量的两个关键因素:结构和纹理,作为未来修复网络设计的方向。

英文摘要:

Deep image inpainting has made impressive progress with recent advances in image generation and processing algorithms. We claim that the performance of inpainting algorithms can be better judged by the generated structures and textures. Structures refer to the generated object boundary or novel geometric structures within the hole, while texture refers to high-frequency details, especially man-made repeating patterns filled inside the structural regions. We believe that better structures are usually obtained from a coarse-to-fine GAN-based generator network while repeating patterns nowadays can be better modeled using state-of-the-art high-frequency fast fourier convolutional layers. In this paper, we propose a novel inpainting network combining the advantages of the two designs. Therefore, our model achieves a remarkable visual quality to match state-of-the-art performance in both structure generation and repeating texture synthesis using a single network. Extensive experiments demonstrate the effectiveness of the method, and our conclusions further highlight the two critical factors of image inpainting quality, structures, and textures, as the future design directions of inpainting networks.

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。

↑