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 1–50 of 212 papers

TitleStatusHype
Moving Object Segmentation: All You Need Is SAM (and Flow)Code3
DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic EnvironmentsCode2
ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the WildCode2
RaTrack: Moving Object Detection and Tracking with 4D Radar Point CloudCode2
Distilled Semantics for Comprehensive Scene Understanding from VideosCode1
Event-Based Motion Segmentation by Motion CompensationCode1
Event-based Motion Segmentation with Spatio-Temporal Graph CutsCode1
MOD-UV: Learning Mobile Object Detectors from Unlabeled VideosCode1
Monocular Arbitrary Moving Object Discovery and SegmentationCode1
Segmenting Moving Objects via an Object-Centric Layered RepresentationCode1
Learning to Segment Rigid Motions from Two FramesCode1
Formulating Event-based Image Reconstruction as a Linear Inverse Problem with Deep Regularization using Optical FlowCode1
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual GroupingCode1
FlowNet3D: Learning Scene Flow in 3D Point CloudsCode1
Sparse Subspace Clustering: Algorithm, Theory, and ApplicationsCode1
Understanding Dynamic Scenes using Graph Convolution NetworksCode1
Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal SupervisionCode1
SSTVOS: Sparse Spatiotemporal Transformers for Video Object SegmentationCode1
HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object InteractionCode1
Discovering Objects that Can MoveCode1
Local Frequency Domain Transformer Networks for Video PredictionCode1
Motion2Language, unsupervised learning of synchronized semantic motion segmentationCode1
Event-based Motion Segmentation by Cascaded Two-Level Multi-Model FittingCode1
MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan SynchronizationCode1
Video Class Agnostic Segmentation Benchmark for Autonomous DrivingCode1
Motion Segmentation using Frequency Domain Transformer NetworksCode1
UnOS: Unified Unsupervised Optical-Flow and Stereo-Depth Estimation by Watching VideosCode1
FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian VelocityCode1
Progressive-X: Efficient, Anytime, Multi-Model Fitting AlgorithmCode1
Self-Supervised Scene Flow Estimation with 4-D Automotive RadarCode1
0-MMS: Zero-Shot Multi-Motion Segmentation With A Monocular Event CameraCode1
EM-driven unsupervised learning for efficient motion segmentationCode1
Robust Motion Segmentation from Pairwise MatchesCode0
Robust Subspace Clustering via Smoothed Rank ApproximationCode0
On the Usage of the Trifocal Tensor in Motion SegmentationCode0
On Matrix Factorizations in Subspace ClusteringCode0
Robust Subspace Clustering via Tighter Rank ApproximationCode0
Nested Grassmannians for Dimensionality Reduction with ApplicationsCode0
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion SegmentationCode0
Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow EstimationCode0
Adaptive Low-Rank Kernel Subspace ClusteringCode0
Moving Objects Detection with a Moving Camera: A Comprehensive ReviewCode0
Multi-Class Model Fitting by Energy Minimization and Mode-SeekingCode0
OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous DrivingCode0
Motion-based Object Segmentation based on Dense RGB-D Scene FlowCode0
KDMOS:Knowledge Distillation for Motion SegmentationCode0
Learning Articulated Motions From Visual DemonstrationCode0
Iterative Event-based Motion Segmentation by Variational Contrast MaximizationCode0
Motion Segmentation by Exploiting Complementary Geometric ModelsCode0
GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene FlowCode0
Show:102550
← PrevPage 1 of 5Next →
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