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
RaTrack: Moving Object Detection and Tracking with 4D Radar Point CloudCode2
ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the WildCode2
DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic EnvironmentsCode2
Segmenting Moving Objects via an Object-Centric Layered RepresentationCode1
Event-based Motion Segmentation with Spatio-Temporal Graph CutsCode1
Event-Based Motion Segmentation by Motion CompensationCode1
MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan SynchronizationCode1
Understanding Dynamic Scenes using Graph Convolution NetworksCode1
SSTVOS: Sparse Spatiotemporal Transformers for Video Object SegmentationCode1
Video Class Agnostic Segmentation Benchmark for Autonomous DrivingCode1
Distilled Semantics for Comprehensive Scene Understanding from VideosCode1
MOD-UV: Learning Mobile Object Detectors from Unlabeled VideosCode1
Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal SupervisionCode1
Formulating Event-based Image Reconstruction as a Linear Inverse Problem with Deep Regularization using Optical FlowCode1
Local Frequency Domain Transformer Networks for Video PredictionCode1
FlowNet3D: Learning Scene Flow in 3D Point CloudsCode1
Learning to Segment Rigid Motions from Two FramesCode1
Motion Segmentation using Frequency Domain Transformer NetworksCode1
Discovering Objects that Can MoveCode1
Progressive-X: Efficient, Anytime, Multi-Model Fitting AlgorithmCode1
Sparse Subspace Clustering: Algorithm, Theory, and ApplicationsCode1
Event-based Motion Segmentation by Cascaded Two-Level Multi-Model FittingCode1
Self-Supervised Scene Flow Estimation with 4-D Automotive RadarCode1
FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian VelocityCode1
0-MMS: Zero-Shot Multi-Motion Segmentation With A Monocular Event CameraCode1
Motion2Language, unsupervised learning of synchronized semantic motion segmentationCode1
Monocular Arbitrary Moving Object Discovery and SegmentationCode1
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual GroupingCode1
HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object InteractionCode1
UnOS: Unified Unsupervised Optical-Flow and Stereo-Depth Estimation by Watching VideosCode1
EM-driven unsupervised learning for efficient motion segmentationCode1
Contour Flow: Middle-Level Motion Estimation by Combining Motion Segmentation and Contour Alignment—0
Context-Aware Modeling and Recognition of Activities in Video—0
Automatic Right Ventricle Segmentation using Multi-Label Fusion in Cardiac MRI—0
Constructing the L2-Graph for Robust Subspace Learning and Subspace Clustering—0
Constructing the F-Graph with a Symmetric Constraint for Subspace Clustering—0
A Unified Model Selection Technique for Spectral Clustering Based Motion Segmentation—0
A Detailed Rubric for Motion Segmentation—0
Consistency and Diversity induced Human Motion Segmentation—0
Attentive and Contrastive Learning for Joint Depth and Motion Field Estimation—0
A Continuous Occlusion Model for Road Scene Understanding—0
Community Recovery in Hypergraphs—0
Dynamic Body VSLAM with Semantic Constraints—0
Coherent Motion Segmentation in Moving Camera Videos using Optical Flow Orientations—0
Appearance-Based Refinement for Object-Centric Motion Segmentation—0
3D Rigid Motion Segmentation with Mixed and Unknown Number of Models—0
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction—0
Dynamics Enhanced Multi-Camera Motion Segmentation From Unsynchronized Videos—0
EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation—0
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