• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >PEPSI++: Fast and Lightweight Network for Image Inpainting
【24h】

PEPSI++: Fast and Lightweight Network for Image Inpainting

机译：Pepsi ++：用于图像染色的快速轻量级网络

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Among the various generative adversarial network (GAN)-based image inpainting methods, a coarse-to-fine network with a contextual attention module (CAM) has shown remarkable performance. However, due to two stacked generative networks, the coarse-to-fine network needs numerous computational resources, such as convolution operations and network parameters, which result in low speed. To address this problem, we propose a novel network architecture called parallel extended-decoder path for semantic inpainting (PEPSI) network, which aims at reducing the hardware costs and improving the inpainting performance. PEPSI consists of a single shared encoding network and parallel decoding networks called coarse and inpainting paths. The coarse path produces a preliminary inpainting result to train the encoding network for the prediction of features for the CAM. Simultaneously, the inpainting path generates higher inpainting quality using the refined features reconstructed via the CAM. In addition, we propose Diet-PEPSI that significantly reduces the network parameters while maintaining the performance. In Diet-PEPSI, to capture the global contextual information with low hardware costs, we propose novel rate-adaptive dilated convolutional layers that employ the common weights but produce dynamic features depending on the given dilation rates. Extensive experiments comparing the performance with state-of-the-art image inpainting methods demonstrate that both PEPSI and Diet-PEPSI improve the qualitative scores, i.e., the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), as well as significantly reduce hardware costs, such as computational time and the number of network parameters.
机译：在各种生成的对抗网络（GAN）中，基于图像染色方法，具有上下文模块（CAM）的粗内网络已经显示出显着的性能。然而，由于两个堆叠的生成网络，粗良好的网络需要许多计算资源，例如卷积操作和网络参数，这导致低速。为了解决这个问题，我们提出了一种新颖的网络架构，称为并行扩展解码器路径，用于语义修复（Pepsi）网络，其旨在降低硬件成本并提高修复性能。 PEPSI由单个共享编码网络和并行解码网络组成，称为粗略和修复路径。粗路径产生初步的修复结果，以训练编码网络以预测凸轮的特征。同时，使用经由凸轮重建的精制特征，确定路径产生更高的初始化质量。此外，我们提出了饮食 - 百事可纲比，在保持性能的同时显着降低了网络参数。在饮食 - 百事可纲比中，以低硬件成本捕获全球背景信息，我们提出了采用共同重量的新型速率适应性扩张的卷积层，但根据给定的扩张速率产生动态特征。通过最先进的图像修复方法比较性能的广泛实验表明，百事可纲和饮食 - 百事可纲比改善了定性分数，即峰值信噪比（PSNR）和结构相似度（SSIM）。以及显着降低硬件成本，例如计算时间和网络参数的数量。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号