A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation

09/19/2022
by   Georgy Ponimatkin, et al.
6

We propose a simple, yet powerful approach for unsupervised 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 relies 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 function can actually be derived from a form of spectral clustering 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.

READ FULL TEXT

page 16

page 17

page 19

page 24

page 25

page 26

page 27

page 28

research
03/23/2022

Unsupervised Salient Object Detection with Spectral Cluster Voting

In this paper, we tackle the challenging task of unsupervised salient ob...
research
03/24/2022

Quantum Motion Segmentation

Motion segmentation is a challenging problem that seeks to identify inde...
research
06/09/2022

VITA: Video Instance Segmentation via Object Token Association

We introduce a novel paradigm for offline Video Instance Segmentation (V...
research
07/05/2019

A Spectral Approach to Unsupervised Object Segmentation in Video

We formulate object segmentation in video as a graph partitioning proble...
research
12/13/2020

Iterative Knowledge Exchange Between Deep Learning and Space-Time Spectral Clustering for Unsupervised Segmentation in Videos

We propose a dual system for unsupervised object segmentation in video, ...
research
04/15/2020

A Transductive Approach for Video Object Segmentation

Semi-supervised video object segmentation aims to separate a target obje...

Please sign up or login with your details

Forgot password? Click here to reset