Papers with Code 아카이브
Motion Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 4
- 보존된 평가 기록
- 11
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
LiDAR-BEVMTN: Real-Time LiDAR Bird's-Eye View Multi-Task Perception Network for Autonomous Driving
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping
Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots
Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision
GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flow
DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments
ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild
Segmenting Moving Objects via an Object-Centric Layered Representation
Segmentation Guided Deep HDR Deghosting
Self-Supervised Deep Subspace Clustering with Entropy-norm
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
Quantum Motion Segmentation
ProgressiveMotionSeg: Mutually Reinforced Framework for Event-Based Motion Segmentation
Discovering Objects that Can Move
HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction
Self-Supervised Scene Flow Estimation with 4-D Automotive Radar
The Right Spin: Learning Object Motion from Rotation-Compensated Flow Fields
Consistency and Diversity induced Human Motion Segmentation
EM-driven unsupervised learning for efficient motion segmentation
Formulating Event-based Image Reconstruction as a Linear Inverse Problem with Deep Regularization using Optical Flow
LiMoSeg: Real-time Bird's Eye View based LiDAR Motion Segmentation
Event-based Motion Segmentation by Cascaded Two-Level Multi-Model Fitting
Unsupervised Object Learning via Common Fate
Attentive and Contrastive Learning for Joint Depth and Motion Field Estimation
NudgeSeg: Zero-Shot Object Segmentation by Repeated Physical Interaction
Graph Constrained Data Representation Learning for Human Motion Segmentation
BEV-MODNet: Monocular Camera based Bird's Eye View Moving Object Detection for Autonomous Driving
On Matrix Factorizations in Subspace Clustering
Unsupervised Video Prediction from a Single Frame by Estimating 3D Dynamic Scene Structure
Weighted Sparse Subspace Representation: A Unified Framework for Subspace Clustering, Constrained Clustering, and Active Learning
Uncertainty in Minimum Cost Multicuts for Image and Motion Segmentation
SpikeMS: Deep Spiking Neural Network for Motion Segmentation
Local Frequency Domain Transformer Networks for Video Prediction
Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery
Spherical formulation of geometric motion segmentation constraints in fisheye cameras
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.