arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.09760cs.CV
收藏

通过条件化纹理与结构双重生成实现图像修复

Image Inpainting via Conditional Texture and Structure Dual Generation

State Key Laboratory of Software Development Environment, Beihang University(北京航空航天大学软件开发环境国家重点实验室);School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院)

Xiefan Guo, Hongyu Yang, Di Huang

AI总结:

针对大面积图像修复中结构与纹理交互不足的问题,提出双流 CTSDG 网络,通过 Bi-GFF 和 CFA 耦合生成结构与纹理,在多个数据集上取得更优修复效果。

摘要:

深度生成方法最近通过引入结构先验,在图像修复方面取得了显著进展。然而,由于在结构重建过程中缺乏与图像纹理的适当交互,现有方案在处理大面积破损情形时能力不足,并且通常会产生失真结果。本文提出一种用于图像修复的新型双流网络,以耦合方式对受结构约束的纹理合成与纹理引导的结构重建进行建模,使二者更好地相互利用,从而实现更合理的生成。此外,为增强全局一致性,设计了双向门控特征融合(Bi-GFF)模块以交换并组合结构与纹理信息,并开发了上下文特征聚合(CFA)模块,通过区域亲和性学习和多尺度特征聚合来细化生成内容。在 CelebA、Paris StreetView 和 Places2 数据集上的定性与定量实验证明了所提方法的优越性。代码可在 https://github.com/Xiefan-Guo/CTSDG 获取。

英文摘要:

Deep generative approaches have recently made considerable progress in image inpainting by introducing structure priors. Due to the lack of proper interaction with image texture during structure reconstruction, however, current solutions are incompetent in handling the cases with large corruptions, and they generally suffer from distorted results. In this paper, we propose a novel two-stream network for image inpainting, which models the structure-constrained texture synthesis and texture-guided structure reconstruction in a coupled manner so that they better leverage each other for more plausible generation. Furthermore, to enhance the global consistency, a Bi-directional Gated Feature Fusion (Bi-GFF) module is designed to exchange and combine the structure and texture information and a Contextual Feature Aggregation (CFA) module is developed to refine the generated contents by region affinity learning and multi-scale feature aggregation. Qualitative and quantitative experiments on the CelebA, Paris StreetView and Places2 datasets demonstrate the superiority of the proposed method. Our code is available at https://github.com/Xiefan-Guo/CTSDG.

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。

↑