arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.08692cs.CVcs.GR
收藏

DeepRemaster:用于综合视频增强的时间源参考注意网络

DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement

University of Tsukuba(筑波大学);Waseda University(早稻田大学);JST PRESTO(日本科学技术振兴机构 PRESTO 计划)

Satoshi Iizuka, Edgar Simo-Serra

摘要:

复古电影的重制包括多种子任务,包括超分辨率,噪音消除和对比度增强,旨在将劣化的电影介质恢复到其原始状态。此外,由于当时的技术限制,大多数老式电影要么以黑白记录,要么具有低质量的颜色,因此需要彩色化。在这项工作中,我们提出了一个单一的框架来解决整个重制任务半交互式。我们的工作是基于时间卷积神经网络与注意力机制训练的视频与数据驱动的恶化模拟。我们提出的源参考注意力允许模型处理任意数量的参考彩色图像来着色长视频,而无需分割,同时保持时间一致性。定量分析表明,我们的框架优于现有的方法,并且,与现有的方法相比,我们的框架的性能随着视频的长度和参考彩色图像的增加而增加。

英文摘要:

The remastering of vintage film comprises of a diversity of sub-tasks including super-resolution, noise removal, and contrast enhancement which aim to restore the deteriorated film medium to its original state. Additionally, due to the technical limitations of the time, most vintage film is either recorded in black and white, or has low quality colors, for which colorization becomes necessary. In this work, we propose a single framework to tackle the entire remastering task semi-interactively. Our work is based on temporal convolutional neural networks with attention mechanisms trained on videos with data-driven deterioration simulation. Our proposed source-reference attention allows the model to handle an arbitrary number of reference color images to colorize long videos without the need for segmentation while maintaining temporal consistency. Quantitative analysis shows that our framework outperforms existing approaches, and that, in contrast to existing approaches, the performance of our framework increases with longer videos and more reference color images.

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。

↑