Abstract: We propose a simple, yet powerful approach for unsu- pervised object segmentation in videos. We introduce an objective function whose minimum represents the mask of the main salient object over the input sequence. It only re- lies on independent image features and optical flows, which can be obtained using off-the-shelf self-supervised methods. It scales with the length of the sequence with no need for superpixels or sparsification, and it generalizes to different datasets without any specific training. This objective func- tion can actually be derived from a form of spectral clus- tering applied to the entire video. Our method achieves on-par performance with the state of the art on standard benchmarks (DAVIS2016, SegTrack-v2, FBMS59), while being conceptually and practically much simpler. Code is available at https://ponimatkin.github.io/ ssl-vos.
0 Replies
Loading