Motion Segmentation
54 papers with code • 4 benchmarks • 7 datasets
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.
Benchmarks
These leaderboards are used to track progress in Motion Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Hopkins155
ApolloScape
EV-IMO
KT3DMoSeg
KITTI'15 MSplus
Most implemented papers
UnOS: Unified Unsupervised Optical-Flow and Stereo-Depth Estimation by Watching Videos
baidu-research/UnDepthflow
•
•
CVPR 2019
In this paper, we propose UnOS, an unified system for unsupervised optical flow and stereo depth estimation using convolutional neural network (CNN) by taking advantages of their inherent geometrical consistency based on the rigid-scene assumption.
Distilled Semantics for Comprehensive Scene Understanding from Videos
CVLAB-Unibo/omeganet
•
•
CVPR 2020
Whole understanding of the surroundings is paramount to autonomous systems.
Motion Segmentation using Frequency Domain Transformer Networks
AIS-Bonn/MotionSegmentation
•
•
Self-supervised prediction is a powerful mechanism to learn representations that capture the underlying structure of the data.
Understanding Dynamic Scenes using Graph Convolution Networks
ma8sa/Undersrtanding-Dynamic-Scenes-using-MR-GCN
•
•
We present a novel Multi-Relational Graph Convolutional Network (MRGCN) based framework to model on-road vehicle behaviors from a sequence of temporally ordered frames as grabbed by a moving monocular camera.
0-MMS: Zero-Shot Multi-Motion Segmentation With A Monocular Event Camera
Segmentation of moving objects in dynamic scenes is a key process in scene understanding for navigation tasks.
Nested Grassmannians for Dimensionality Reduction with Applications
With the proposed NG structure, we develop algorithms for the supervised and unsupervised dimensionality reduction problems respectively.
Event-based Motion Segmentation with Spatio-Temporal Graph Cuts
We develop a method to identify independently moving objects acquired with an event-based camera, i. e., to solve the event-based motion segmentation problem.
Learning to Segment Rigid Motions from Two Frames
gengshan-y/rigidmask
•
•
CVPR 2021
Geometric motion segmentation algorithms, however, generalize to novel scenes, but have yet to achieve comparable performance to appearance-based ones, due to noisy motion estimations and degenerate motion configurations.
MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization
huangjh-pub/multibody-sync
•
•
CVPR 2021
We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds.
SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation
SST extracts per-pixel representations for each object in a video using sparse attention over spatiotemporal features.
