arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.11208cs.CV
收藏

基于时空对齐和聚合的深度视频抠图

Deep Video Matting via Spatio-Temporal Alignment and Aggregation

HKUST(香港科技大学);Stanford University(斯坦福大学);Carnegie Mellon University(卡内基梅隆大学);Kuaishou Technology(快手科技)

Yanan Sun, Guanzhi Wang, Qiao Gu, Chi-Keung Tang, Yu-Wing Tai

摘要:

尽管深度学习在自然图像抠图方面取得了重大进展,但由于时间域推理固有的技术挑战和缺乏大规模视频抠图数据集,到目前为止还没有针对视频抠图的深度学习的代表性工作。在本文中,我们提出了一个基于深度学习的视频抠图框架,它采用了一种新颖而有效的时空特征聚合模块(ST-FAM)。由于光流估计在遮片区域内可能非常不可靠,因此ST-FAM被设计为在网络解码器内跨不同空间尺度和时间帧有效地对准和聚合信息。为了消除逐帧的trimap注释,还引入了轻量级交互式trimap传播网络。另一个贡献包括一个大规模的视频抠图数据集,其中包含用于定量评估的groundtruth alpha抠图和用于定性评估的真实世界高分辨率视频。定量和定性的实验结果表明,我们的框架显着优于传统的视频抠图和深度图像抠图方法应用于视频中存在的多帧时间信息。

英文摘要:

Despite the significant progress made by deep learning in natural image matting, there has been so far no representative work on deep learning for video matting due to the inherent technical challenges in reasoning temporal domain and lack of large-scale video matting datasets. In this paper, we propose a deep learning-based video matting framework which employs a novel and effective spatio-temporal feature aggregation module (ST-FAM). As optical flow estimation can be very unreliable within matting regions, ST-FAM is designed to effectively align and aggregate information across different spatial scales and temporal frames within the network decoder. To eliminate frame-by-frame trimap annotations, a lightweight interactive trimap propagation network is also introduced. The other contribution consists of a large-scale video matting dataset with groundtruth alpha mattes for quantitative evaluation and real-world high-resolution videos with trimaps for qualitative evaluation. Quantitative and qualitative experimental results show that our framework significantly outperforms conventional video matting and deep image matting methods applied to video in presence of multi-frame temporal information.

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。

↑