修补
计算机科学
变压器
图像(数学)
人工智能
源代码
计算机视觉
算法
模式识别(心理学)
工程类
电压
操作系统
电气工程
作者
Keunsoo Ko,Chang‐Su Kim
标识
DOI:10.1109/iccv51070.2023.01211
摘要
A novel continuous-mask-aware transformer for image inpainting, called CMT, is proposed in this paper, which uses a continuous mask to represent the amounts of errors in tokens. First, we initialize a mask and use it during the self-attention. To facilitate the masked self-attention, we also introduce the notion of overlapping tokens. Second, we update the mask by modeling the error propagation during the masked self-attention. Through several masked self-attention and mask update (MSAU) layers, we predict initial inpainting results. Finally, we refine the initial results to reconstruct a more faithful image. Experimental results on multiple datasets show that the proposed CMT algorithm outperforms existing algorithms significantly. The source codes are available at https://github.com/keunsoo-ko/CMT.
科研通智能强力驱动
Strongly Powered by AbleSci AI