Unsupervised Video Object Segmentation

45 papers with code • 6 benchmarks • 7 datasets

The unsupervised scenario assumes that the user does not interact with the algorithm to obtain the segmentation masks. Methods should provide a set of object candidates with no overlapping pixels that span through the whole video sequence. This set of objects should contain at least the objects that capture human attention when watching the whole video sequence i.e objects that are more likely to be followed by human gaze.

Most implemented papers

EpO-Net: Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency

mfaisal59/EpONet WACV 2020

To handle the nonrigid background like a sea, we also propose a robust fusion mechanism between motion and appearance-based features.

Tukey-Inspired Video Object Segmentation

griffbr/TIS 19 Nov 2018

We investigate the problem of strictly unsupervised video object segmentation, i. e., the separation of a primary object from background in video without a user-provided object mask or any training on an annotated dataset.

Joint-task Self-supervised Learning for Temporal Correspondence

Liusifei/UVC NeurIPS 2019

Our learning process integrates two highly related tasks: tracking large image regions \emph{and} establishing fine-grained pixel-level associations between consecutive video frames.

MAST: A Memory-Augmented Self-supervised Tracker

zlai0/MAST CVPR 2020

Recent interest in self-supervised dense tracking has yielded rapid progress, but performance still remains far from supervised methods.

Video Object Segmentation using Supervoxel-Based Gerrymandering

griffbr/supervoxel-gerrymandering 18 Apr 2017

Focusing on the problem of strictly unsupervised video object segmentation, we devise a method called supervoxel gerrymandering that links masks of foregroundness and backgroundness via local and non-local consensus measures.

SegFlow: Joint Learning for Video Object Segmentation and Optical Flow

JingchunCheng/SegFlow ICCV 2017

This paper proposes an end-to-end trainable network, SegFlow, for simultaneously predicting pixel-wise object segmentation and optical flow in videos.

Unsupervised Video Object Segmentation for Deep Reinforcement Learning

vik-goel/MOREL NeurIPS 2018

The detection of moving objects is done in an unsupervised way by exploiting structure from motion.

Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection

shenjianbing/PDB-ConvLSTM ECCV 2018

This paper proposes a fast video salient object detection model, based on a novel recurrent network architecture, named Pyramid Dilated Bidirectional ConvLSTM (PDB-ConvLSTM).

Extending Layered Models to 3D Motion

donglao/layers3Dmotion ECCV 2018

We consider the problem of inferring a layered representa-tion, its depth ordering and motion segmentation from a video in whichobjects may undergo 3D non-planar motion relative to the camera.

Unsupervised Online Video Object Segmentation with Motion Property Understanding

VisionTao/UOVOS IEEE Transactions on Image Processing 2019

Moreover, our method achieves better performance than the best unsupervised offline algorithm on the DAVIS-2016 benchmark dataset.