arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.03356cs.CV
收藏

SPG-Net:用于图像修补的分割预测和引导网络

SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting

University of Southern California(南加州大学);Baidu Research(百度研究院)

Yuhang Song, Chao Yang, Yeji Shen, Peng Wang, Qin Huang, C. -C. Jay Kuo

摘要:

在本文中,我们专注于图像修补任务,旨在恢复一个不完整的图像的上下文信息的缺失区域。深度生成模型的最新发展为图像合成和修复任务提供了一个有效的端到端框架,但基于生成模型的现有方法没有利用分割信息来约束对象形状,这通常会导致边界上的模糊结果。为了解决这个问题,我们提出了引入语义分割信息,它解开类间差异和类内变化的图像修补。这导致语义上不同的区域之间的更清晰的恢复边界和语义上一致的片段内的更好的纹理。该模型将图像修补过程分解为分割预测(SP-Net)和分割指导(SG-Net)两个步骤,首先预测缺失区域的分割标签,然后生成分割指导的修补结果。在多个公共数据集上的实验表明,该方法在优化图像修补质量方面优于现有方法,并且交互式分割指导为图像修补的多模态预测提供了可能。

英文摘要:

In this paper, we focus on image inpainting task, aiming at recovering the missing area of an incomplete image given the context information. Recent development in deep generative models enables an efficient end-to-end framework for image synthesis and inpainting tasks, but existing methods based on generative models don't exploit the segmentation information to constrain the object shapes, which usually lead to blurry results on the boundary. To tackle this problem, we propose to introduce the semantic segmentation information, which disentangles the inter-class difference and intra-class variation for image inpainting. This leads to much clearer recovered boundary between semantically different regions and better texture within semantically consistent segments. Our model factorizes the image inpainting process into segmentation prediction (SP-Net) and segmentation guidance (SG-Net) as two steps, which predict the segmentation labels in the missing area first, and then generate segmentation guided inpainting results. Experiments on multiple public datasets show that our approach outperforms existing methods in optimizing the image inpainting quality, and the interactive segmentation guidance provides possibilities for multi-modal predictions of image inpainting.

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。

↑