论文标题
用压缩压缩网络覆盖大孔图像
Large Hole Image Inpainting With Compress-Decompression Network
论文作者
论文摘要
图像介入技术可以用缺少像素来修补图像。现有方法建议卷积神经网络修复损坏的图像。网络专注于丢失像素周围的有效像素，使用编码器解码器结构提取有价值的信息，并使用信息来修复空缺。但是，如果丢失的部分太大而无法提供有用的信息，则结果将存在模糊，颜色混合和对象混乱。为了修补大孔图像，我们研究了现有方法，并提出了一个新网络，即压缩压缩网络。压缩网络负责对下样本图像进行介绍和生成。减压网络负责将下样本图像扩展到原始分辨率。我们使用残留网络构建压缩网络，并提出类似的纹理选择算法，以扩展比使用超分辨率网络更好的图像。我们将模型评估为Ploce2和Celeba数据集，并将相似性比作为度量标准。结果表明，当介绍任务有许多冲突时，我们的模型具有更好的性能。
Image inpainting technology can patch images with missing pixels. Existing methods propose convolutional neural networks to repair corrupted images. The networks focus on the valid pixels around the missing pixels, use the encoder-decoder structure to extract valuable information, and use the information to fix the vacancy. However, if the missing part is too large to provide useful information, the result will exist blur, color mixing, and object confusion. In order to patch the large hole image, we study the existing approaches and propose a new network, the compression-decompression network. The compression network takes responsibility for inpainting and generating a down-sample image. The decompression network takes responsibility for extending the down-sample image into the original resolution. We construct the compression network with the residual network and propose a similar texture selection algorithm to extend the image that is better than using the super-resolution network. We evaluate our model over Places2 and CelebA data set and use the similarity ratio as the metric. The result shows that our model has better performance when the inpainting task has many conflicts.
