arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.08003cs.CVeess.IV
收藏

基于多通道相关的任意视频格式传输

Arbitrary Video Style Transfer via Multi-Channel Correlation

University of Chinese Academy of Sciences(中国科学院大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Jilin University(吉林大学);Kuaishou Technology(快手科技)

Yingying Deng, Fan Tang, Weiming Dong, Haibin Huang, Chongyang Ma, Changsheng Xu

摘要:

视频风格转换因其在增强现实和动画制作等领域的广泛应用而受到人工智能界的关注。与传统的图像风格转换相比,在视频上执行此任务提出了新的挑战:如何有效地生成令人满意的风格化结果,为任何指定的风格,并保持跨帧的时间一致性在同一时间。为此,我们提出了多通道校正网络(MCCNet),它可以被训练来融合范例风格特征和输入内容特征,以实现高效的风格转换,同时自然地保持输入视频的连贯性。具体来说,MCCNet直接作用于样式和内容域的特征空间,在那里它学会根据样式特征与内容特征的相似性重新排列和融合样式特征。MCC生成的输出是包含所需样式模式的特征,这些样式模式可以进一步解码为具有生动样式纹理的图像。此外,MCCNet还被设计为显式地将特征与输入对齐,以确保输出保持内容结构以及时间连续性。为了进一步提高MCCNet在复杂光照条件下的性能,我们还在训练过程中引入了光照损失。定性和定量的评估表明,MCCNet在任意视频和图像风格的传输任务中表现良好。

英文摘要:

Video style transfer is getting more attention in AI community for its numerous applications such as augmented reality and animation productions. Compared with traditional image style transfer, performing this task on video presents new challenges: how to effectively generate satisfactory stylized results for any specified style, and maintain temporal coherence across frames at the same time. Towards this end, we propose Multi-Channel Correction network (MCCNet), which can be trained to fuse the exemplar style features and input content features for efficient style transfer while naturally maintaining the coherence of input videos. Specifically, MCCNet works directly on the feature space of style and content domain where it learns to rearrange and fuse style features based on their similarity with content features. The outputs generated by MCC are features containing the desired style patterns which can further be decoded into images with vivid style textures. Moreover, MCCNet is also designed to explicitly align the features to input which ensures the output maintains the content structures as well as the temporal continuity. To further improve the performance of MCCNet under complex light conditions, we also introduce the illumination loss during training. Qualitative and quantitative evaluations demonstrate that MCCNet performs well in both arbitrary video and image style transfer tasks.

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。

↑