Video segmentation approaches are of great importance for numerous vision tasks especially in video manipulation for entertainment. Due to the challenges associated with acquiring high-quality per-frame segmentation annotations and large video datasets with different environments at scale, learning approaches shows overall higher accuracy on test dataset but lack strict temporal constraints to self-correct jittering artifacts in most practical applications. We investigate how this jittering artifact degrades the visual quality of video segmentation results and proposed a metric of temporal stability to numerically evaluate it. In particular, we propose a Coherent Loss with a generic framework to enhance the performance of a neural network against jittering artifacts, which combines with high accuracy and high consistency. Equipped with our method, existing video object/semantic segmentation approaches achieve a significant improvement in term of more satisfactory visual quality on video human dataset, which we provide for further research in this field, and also on DAVIS and Cityscape.
@article{arxiv.2010.13085,
title = {Coherent Loss: A Generic Framework for Stable Video Segmentation},
author = {Mingyang Qian and Yi Fu and Xiao Tan and Yingying Li and Jinqing Qi and Huchuan Lu and Shilei Wen and Errui Ding},
journal= {arXiv preprint arXiv:2010.13085},
year = {2020}
}