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 126–150 of 212 papers

TitleStatusHype
Using Motion and Internal Supervision in Object Recognition—0
Object Discovery in Videos as Foreground Motion Clustering—0
Extending Layered Models to 3D MotionCode0
Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow EstimationCode0
The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation—0
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion SegmentationCode0
Motion-based Object Segmentation based on Dense RGB-D Scene FlowCode0
Image Segmentation Using Subspace Representation and Sparse Decomposition—0
Motion Segmentation by Exploiting Complementary Geometric ModelsCode0
Fast Piecewise-Affine Motion Estimation Without Segmentation—0
Self-Supervised Relative Depth Learning for Urban Scene Understanding—0
Learning to Segment Moving Objects—0
CUR Decompositions, Similarity Matrices, and Subspace Clustering—0
Dynamics Enhanced Multi-Camera Motion Segmentation From Unsynchronized Videos—0
MODNet: Moving Object Detection Network with Motion and Appearance for Autonomous Driving—0
Community Recovery in Hypergraphs—0
A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models—0
Adaptive Low-Rank Kernel Subspace ClusteringCode0
Fast Multi-frame Stereo Scene Flow with Motion Segmentation—0
Coarse-To-Fine Segmentation With Shape-Tailored Continuum Scale Spaces—0
Multi-Class Model Fitting by Energy Minimization and Mode-SeekingCode0
Learning Video Object Segmentation with Visual Memory—0
Joint Semantic and Motion Segmentation for dynamic scenes using Deep Convolutional Networks—0
Higher-Order Minimum Cost Lifted Multicuts for Motion Segmentation—0
Motion Segmentation via Global and Local Sparse Subspace Optimization—0
Show:102550
← PrevPage 6 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