arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.10753cs.CVcs.AI
收藏

基于语义指导的交互式图像修补

Interactive Image Inpainting Using Semantic Guidance

Communication and Information Security Lab Shenzhen Graduate School, Peking University(北京大学深圳研究生院通信与信息安全实验室)

Wangbo Yu, Jinhao Du, Ruixin Liu, Yixuan Li, Yuesheng zhu

摘要:

在深度神经网络的帮助下,图像修补方法取得了重大进展。然而,现有的方法主要集中在利用神经网络学习的先验分布来产生单个修复结果或进一步产生多个解决方案,其中可控性没有得到很好的研究。本文提出了一种新的图像修补方法,使用户能够根据自己的喜好或记忆定制修补结果。具体来说,我们的方法是由两个阶段,利用神经网络和用户的指导,联合修复损坏的图像。在第一阶段中,一个自动编码器的基础上,一种新的外部空间注意力机制被部署到产生的损坏的图像和粗糙的修复结果,提供语义掩模作为用户交互的媒介重建功能。在第二阶段,采用语义解码器,以重建的特征作为优先级,合成一个精细的修复结果由用户的自定义语义掩模的指导下,使最终的修复结果将共享相同的内容与用户的指导,而在第一阶段重建的纹理和颜色被保留。大量的实验表明,我们的方法在修复质量和可控性方面的优越性。

英文摘要:

Image inpainting approaches have achieved significant progress with the help of deep neural networks. However, existing approaches mainly focus on leveraging the priori distribution learned by neural networks to produce a single inpainting result or further yielding multiple solutions, where the controllability is not well studied. This paper develops a novel image inpainting approach that enables users to customize the inpainting result by their own preference or memory. Specifically, our approach is composed of two stages that utilize the prior of neural network and user's guidance to jointly inpaint corrupted images. In the first stage, an autoencoder based on a novel external spatial attention mechanism is deployed to produce reconstructed features of the corrupted image and a coarse inpainting result that provides semantic mask as the medium for user interaction. In the second stage, a semantic decoder that takes the reconstructed features as prior is adopted to synthesize a fine inpainting result guided by user's customized semantic mask, so that the final inpainting result will share the same content with user's guidance while the textures and colors reconstructed in the first stage are preserved. Extensive experiments demonstrate the superiority of our approach in terms of inpainting quality and controllability.

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。

↑