Video Matting via Consistency-Regularized Graph Neural Networks

Tiantian Wang, Sifei Liu, Yapeng Tian, Kai Li, Ming-Hsuan Yang; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 4902-4911

Abstract


Learning temporally consistent foreground opacity from videos, i.e., video matting, has drawn great attention due to the blossoming of video conferencing. Previous approaches are built on top of image matting models, which fail in maintaining the temporal coherence when being adapted to videos. They either utilize the optical flow to smooth frame-wise prediction, where the performance is dependent on the selected optical flow model; or naively combine feature maps from multiple frames, which does not model well the correspondence of pixels in adjacent frames. In this paper, we propose to enhance the temporal coherence by Consistency-Regularized Graph Neural Networks (CRGNN) with the aid of a synthesized video matting dataset. CRGNN utilizes Graph Neural Networks (GNN) to relate adjacent frames such that pixels or regions that are incorrectly predicted in one frame can be corrected by leveraging information from its neighboring frames. To generalize our model from synthesized videos to real-world videos, we propose a consistency regularization technique to enforce the consistency on the alpha and foreground when blending them with different backgrounds. To evaluate the efficacy of CRGNN, we further collect a real-world dataset with annotated alpha mattes. Compared with state-of-the-art methods that require hand-crafted trimaps or backgrounds for modeling training, CRGNN generates favorably results with the help of unlabeled real training dataset.

Related Material


[pdf]
[bibtex]
@InProceedings{Wang_2021_ICCV, author = {Wang, Tiantian and Liu, Sifei and Tian, Yapeng and Li, Kai and Yang, Ming-Hsuan}, title = {Video Matting via Consistency-Regularized Graph Neural Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {4902-4911} }