SOTAVerified

Motion Segmentation

Motion Segmentation is an essential task in many applications in Computer Vision and Robotics, such as surveillance, action recognition and scene understanding. The classic way to state the problem is the following: given a set of feature points that are tracked through a sequence of images, the goal is to cluster those trajectories according to the different motions they belong to. It is assumed that the scene contains multiple objects that are moving rigidly and independently in 3D-space.

Source: Robust Motion Segmentation from Pairwise Matches

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–125 of 212 papers

TitleStatusHype
Quantum Motion Segmentation—0
Quickest Moving Object Detection—0
Reconstructing Articulated Rigged Models from RGB-D Videos—0
ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering—0
Retina-Inspired Object Motion Segmentation for Event-Cameras—0
Rigid Motion Segmentation using Randomized Voting—0
Robust Multi-body Feature Tracker: A Segmentation-free Approach—0
Robust Real-time RGB-D Visual Odometry in Dynamic Environments via Rigid Motion Model—0
Robust Subspace Segmentation with Block-diagonal Prior—0
Robust Video Background Identification by Dominant Rigid Motion Estimation—0
ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images—0
RoMo: Robust Motion Segmentation Improves Structure from Motion—0
Scalable Sparse Subspace Clustering—0
Scene Flow from Point Clouds with or without Learning—0
Segmentation-Free Dynamic Scene Deblurring—0
Segmentation Guided Deep HDR Deghosting—0
Self-Supervised Deep Subspace Clustering with Entropy-norm—0
Self-Supervised Relative Depth Learning for Urban Scene Understanding—0
Self-supervised Sparse to Dense Motion Segmentation—0
Self-supervised Video Object Segmentation by Motion Grouping—0
Semantic Motion Segmentation Using Dense CRF Formulation—0
Simultaneous Localization, Mapping, and Manipulation for Unsupervised Object Discovery—0
SLIM: Self-Supervised LiDAR Scene Flow and Motion Segmentation—0
Spherical formulation of geometric motion segmentation constraints in fisheye cameras—0
SpikeMS: Deep Spiking Neural Network for Motion Segmentation—0
Show:102550
← PrevPage 5 of 9Next →
All datasetsApolloScapeHopkins155KT3DMoSegMTPV62

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Rule BasedAccuracy90—Unverified
2Rel-Att-GCNAccuracy89—Unverified
3MRGCNAccuracy86—Unverified
4MRGCN-LSTMAccuracy72—Unverified
5St-RNNAccuracy63—Unverified
#ModelMetricClaimedVerifiedStatus
1SSCClassification Error2.18—Unverified
2T-LinkageClassification Error1.97—Unverified
3RSIMClassification Error1.01—Unverified
4MVCClassification Error0.31—Unverified
#ModelMetricClaimedVerifiedStatus
1MultiViewClusteringError7.92—Unverified
#ModelMetricClaimedVerifiedStatus
1MVCClassification Error0.65—Unverified