并行生成卷积网络图像修复算法

为解决修复纹理精细、背景复杂图像中大面积不连续语义缺失时存在的边缘伪影和语义不连续的缺陷,提出一种并行生成卷积的残差连接图像修复算法。将残缺图像输入一个两列平行卷积的结构修复网络得到两个具有不同感受野大小的图像分量,通过共享解码合并两个图像分量并计算输出的L2损失优化网络。将结构修复网络的输出送入包含残差连接与注意力机制的细节修复网络,融合上下文信息,改善修复细节能力。使用全局与局部鉴别器和预训练视觉几何组网络计算损失,对修复网络进行整体判别优化,增强修复结果的整体与局部一致性。在国际公认数据库上验证提出算法的性能,实验结果表明：提出算法可以有效修复复杂背景且包含精细纹理的大面积不规则缺失区域,提升图像细节、语义和结构的真实性与完整性,其峰值信噪比和结构相似度优于经典的对比算法。

Algorithm on image restoration of parallel generation convolution network

In order to solve the defects of edge artifacts and semantic discontinuity when inpainting large and irregular distortions in an image with fine texture and complex background, a residual connection image restoration algorithm based on parallel generation convolution was proposed. The damaged image was inputted into a two-column parallel convolutional structure inpainting network to obtain two image components with different sizes of reception fields. The two image components were combined by the shared decoding and the L2 loss of the output was calculated to optimize the network. The output of the coarse network was sent into the fine inpainting network which contained the residual connection and the attention mechanism to fuse context information and improve the ability of repairing fine details. The global and local discriminators and visual geometry group net were used to calculate the loss and to optimize the overall discrimination network and enhance the global and local consistency of the inpainting result. The performance of the proposed algorithm was validated on internationally recognized databases, and experimental results show that the proposed algorithm can effectively repair large and irregular missing areas under complex background and fine texture, improve the authenticity and integrity of image details, semantics and structure. Its peak signal-to-noise ratio and structural similarity are superior to the state-of-the-art.