Video Part Segmentation

We apply our part co-segmentation method (Sec. 5.2 in paper) to video frames — we treat the frames from each video as a collection of images, and apply our method without any changes. No temporal information is used. Notice the consistency of object parts through time under large motion varaitions and occlusions in DAVIS [1] and in camouflaged examples in MoCA [2].


MoCA examples

Original Video Part Co-segmentation

DAVIS examples

Original Video Part Co-segmentation


[1] The 2017 DAVIS Challenge on Video Object Segmentation. Pont-Tuset et al. CVPR 2017

[2] Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation. Lamdouar et al. ACCV 2020