Unsupervised Video Object Segmentation
51 papers with code • 6 benchmarks • 8 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.
Benchmarks
These leaderboards are used to track progress in Unsupervised Video Object Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Datasets
DAVIS 2017
DAVIS 2016
FBMS
SegTrack-v2
Referring Expressions for DAVIS 2016 & 2017
MOSE
FBMS-59
BL30K
Latest papers
Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation
NUST-Machine-Intelligence-Laboratory/HFAN
•
•
Optical flow is an easily conceived and precious cue for advancing unsupervised video object segmentation (UVOS).
Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation
xilin1991/IMCNet
•
•
Unsupervised video object segmentation (UVOS) aims at automatically separating the primary foreground object(s) from the background in a video sequence.
In-N-Out Generative Learning for Dense Unsupervised Video Segmentation
By contrast, pixel-level optimization is more explicit, however, it is sensitive to the visual quality of training data and is not robust to object deformation.
Autoencoder-based background reconstruction and foreground segmentation with background noise estimation
The main novelty of the proposed model is that the autoencoder is also trained to predict the background noise, which allows to compute for each frame a pixel-dependent threshold to perform the foreground segmentation.
D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
We further show that D^2Conv3D out-performs trivial extensions of existing dilated and deformable convolutions to 3D.
D2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
schmiddo/d2conv3d
•
•
WACV 2021
We further show that D2Conv3D out-performs trivial extensions of existing dilated and deformable convolutions to 3D.
Dense Unsupervised Learning for Video Segmentation
visinf/dense-ulearn-vos
•
•
NeurIPS 2021
On established VOS benchmarks, our approach exceeds the segmentation accuracy of previous work despite using significantly less training data and compute power.
Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation
xiaoqi-zhao-dlut/multi-source-aps-zvos
•
•
In this paper, we propose a novel multi-source fusion network for zero-shot video object segmentation.
Full-Duplex Strategy for Video Object Segmentation
Previous video object segmentation approaches mainly focus on using simplex solutions between appearance and motion, limiting feature collaboration efficiency among and across these two cues.
Reciprocal Transformations for Unsupervised Video Object Segmentation
OliverRensu/RTNet
•
•
CVPR 2021
Additionally, to exclude the information of the moving background objects from motion features, our transformation module enables to reciprocally transform the appearance features to enhance the motion features, so as to focus on the moving objects with salient appearance while removing the co-moving outliers.
