Unsupervised Video Object Segmentation with Motion-based Bilateral Networks

Siyang Li, Bryan Seybold, Alexey Vorobyov, Xuejing Lei, C.-C. Jay Kuo; Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 207-223

Abstract


In this work, we study the unsupervised video object segmentation problem where moving objects are segmented without prior knowledge of these objects. First, we propose a motion-based bilateral network to estimate the background based on the motion pattern of non-object regions. The bilateral network reduces false positive regions by accurately identifying background objects. Then, we integrate the background estimate from the bilateral network with instance embeddings into a graph, which allows multiple frame reasoning with graph edges linking pixels from different frames. We classify graph nodes by defining and minimizing a cost function, and segment the video frames based on the node labels. The proposed method outperforms previous state-of-the-art unsupervised video object segmentation methods against the DAVIS 2016 and the FBMS-59 datasets.

Related Material


[pdf]
[bibtex]
@InProceedings{Li_2018_ECCV,
author = {Li, Siyang and Seybold, Bryan and Vorobyov, Alexey and Lei, Xuejing and Jay Kuo, C.-C.},
title = {Unsupervised Video Object Segmentation with Motion-based Bilateral Networks},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
month = {September},
year = {2018}
}