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 51–100 of 212 papers

TitleStatusHype
Dense Monocular Motion Segmentation Using Optical Flow and Pseudo Depth Map: A Zero-Shot Approach—0
Motion Segmentation for Neuromorphic Aerial SurveillanceCode0
Zero-Shot Monocular Motion Segmentation in the Wild by Combining Deep Learning with Geometric Motion Model Fusion—0
Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence—0
Neuromorphic Vision-based Motion Segmentation with Graph Transformer Neural Network—0
Out of the Room: Generalizing Event-Based Dynamic Motion Segmentation for Complex Scenes—0
A Unified Model Selection Technique for Spectral Clustering Based Motion Segmentation—0
Learned Trajectory Embedding for Subspace Clustering—0
WoodScape Motion Segmentation for Autonomous Driving -- CVPR 2023 OmniCV Workshop Challenge—0
Appearance-Based Refinement for Object-Centric Motion Segmentation—0
Un-EvMoSeg: Unsupervised Event-based Independent Motion Segmentation—0
Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes—0
Segmenting the motion components of a video: A long-term unsupervised model—0
Motion Segmentation from a Moving Monocular Camera—0
Joint Self-supervised Depth and Optical Flow Estimation towards Dynamic Objects—0
A Multi-Scale Recurrent Framework for Motion Segmentation With Event CameraCode0
LiDAR-BEVMTN: Real-Time LiDAR Bird's-Eye View Multi-Task Perception Network for Autonomous Driving—0
Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots—0
Unsupervised Space-Time Network for Temporally-Consistent Segmentation of Multiple MotionsCode0
GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene FlowCode0
Segmentation Guided Deep HDR Deghosting—0
Self-Supervised Deep Subspace Clustering with Entropy-norm—0
EVIMO2: An Event Camera Dataset for Motion Segmentation, Optical Flow, Structure from Motion, and Visual Inertial Odometry in Indoor Scenes with Monocular or Stereo Algorithms—0
Quantum Motion Segmentation—0
ProgressiveMotionSeg: Mutually Reinforced Framework for Event-Based Motion Segmentation—0
The Right Spin: Learning Object Motion from Rotation-Compensated Flow Fields—0
Consistency and Diversity induced Human Motion Segmentation—0
LiMoSeg: Real-time Bird's Eye View based LiDAR Motion Segmentation—0
Attentive and Contrastive Learning for Joint Depth and Motion Field Estimation—0
Unsupervised Object Learning via Common FateCode0
NudgeSeg: Zero-Shot Object Segmentation by Repeated Physical Interaction—0
Graph Constrained Data Representation Learning for Human Motion SegmentationCode0
BEV-MODNet: Monocular Camera based Bird's Eye View Moving Object Detection for Autonomous Driving—0
On Matrix Factorizations in Subspace ClusteringCode0
Unsupervised Video Prediction from a Single Frame by Estimating 3D Dynamic Scene Structure—0
Weighted Sparse Subspace Representation: A Unified Framework for Subspace Clustering, Constrained Clustering, and Active LearningCode0
Uncertainty in Minimum Cost Multicuts for Image and Motion Segmentation—0
SpikeMS: Deep Spiking Neural Network for Motion Segmentation—0
Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery—0
Spherical formulation of geometric motion segmentation constraints in fisheye cameras—0
Self-supervised Video Object Segmentation by Motion Grouping—0
Deep Learning for Robust Motion Segmentation with Non-Static Cameras—0
OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous DrivingCode0
SLIM: Self-Supervised LiDAR Scene Flow and Motion Segmentation—0
Unsupervised Monocular Depth Reconstruction of Non-Rigid Scenes—0
Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation—0
EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation—0
Scene Flow from Point Clouds with or without Learning—0
Nested Grassmannians for Dimensionality Reduction with ApplicationsCode0
Self-supervised Sparse to Dense Motion Segmentation—0
Show:102550
← PrevPage 2 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