Accelerating Video Object Segmentation with Compressed Video
Abstract
We propose an efficient plug-and-play acceleration framework for semi-supervised video object segmentation by exploiting the temporal redundancies in videos presented by the compressed bitstream. Specifically, we propose a motion vector-based warping method for propagating segmentation masks from keyframes to other frames in a bi-directional and multi-hop manner. Additionally, we introduce a residual-based correction module that can fix wrongly propagated segmentation masks from noisy or erroneous motion vectors. Our approach is flexible and can be added on top of several existing video object segmentation algorithms. We achieved highly competitive results on DAVIS17 and YouTube-VOS on various base models with substantial speed-ups of up to 3.5X with minor drops in accuracy.
Cite
Text
Xu and Yao. "Accelerating Video Object Segmentation with Compressed Video." Conference on Computer Vision and Pattern Recognition, 2022. doi:10.1109/CVPR52688.2022.00140Markdown
[Xu and Yao. "Accelerating Video Object Segmentation with Compressed Video." Conference on Computer Vision and Pattern Recognition, 2022.](https://mlanthology.org/cvpr/2022/xu2022cvpr-accelerating/) doi:10.1109/CVPR52688.2022.00140BibTeX
@inproceedings{xu2022cvpr-accelerating,
title = {{Accelerating Video Object Segmentation with Compressed Video}},
author = {Xu, Kai and Yao, Angela},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2022},
pages = {1342-1351},
doi = {10.1109/CVPR52688.2022.00140},
url = {https://mlanthology.org/cvpr/2022/xu2022cvpr-accelerating/}
}