arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2201.11996eess.IVcs.CV
收藏

用于图像和视频超分辨率的深度网络

Deep Networks for Image and Video Super-Resolution

IPCV Lab, Department of Electrical Engineering, Indian Institute of Technology Madras(印度理工学院马德拉斯分校电气工程系IPCV实验室)

Kuldeep Purohit, Srimanta Mandal, A. N. Rajagopalan

摘要:

卷积神经网络中间层的梯度传播效率对于超分辨率任务至关重要。为此,我们提出了一种用于单图像超分辨率(SISR)的深度架构,该架构使用我们称为混合密集连接块(MDCB)的高效卷积单元构建。MDCB的设计结合了剩余和密集连接策略的优点,同时克服了它们的局限性。为了实现对多个因子的超分辨率,我们提出了一个尺度递归框架,该框架重新利用为较低尺度因子学习的滤波器递归地用于较高的因子。这导致改进的性能,并促进更高因子的参数效率。我们训练我们的网络的两个版本,以提高互补的图像质量使用不同的损失配置。我们进一步将我们的网络用于视频超分辨率任务,在该任务中,我们的网络学习从多帧中聚合信息并保持时空一致性。所提出的网络导致定性和定量的改进,在国家的最先进的技术对图像和视频的超分辨率基准。

英文摘要:

Efficiency of gradient propagation in intermediate layers of convolutional neural networks is of key importance for super-resolution task. To this end, we propose a deep architecture for single image super-resolution (SISR), which is built using efficient convolutional units we refer to as mixed-dense connection blocks (MDCB). The design of MDCB combines the strengths of both residual and dense connection strategies, while overcoming their limitations. To enable super-resolution for multiple factors, we propose a scale-recurrent framework which reutilizes the filters learnt for lower scale factors recursively for higher factors. This leads to improved performance and promotes parametric efficiency for higher factors. We train two versions of our network to enhance complementary image qualities using different loss configurations. We further employ our network for video super-resolution task, where our network learns to aggregate information from multiple frames and maintain spatio-temporal consistency. The proposed networks lead to qualitative and quantitative improvements over state-of-the-art techniques on image and video super-resolution benchmarks.

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。

↑