Papers with Code 아카이브

Motion Segmentation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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.

Source: Robust Motion Segmentation from Pairwise Matches

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/AIS-Bonn/Local_Freq_Transformer_Net

공식 코드

Local Frequency Domain Transformer Networks for Video Prediction

https://github.com/AIS-Bonn/MotionSegmentation

공식 코드

Motion Segmentation using Frequency Domain Transformer Networks

https://github.com/CVLAB-Unibo/omeganet

공식 코드

Distilled Semantics for Comprehensive Scene Understanding from Videos

https://github.com/Etienne-Meunier-Inria/EM-Flow-Segmentation

공식 코드

EM-driven unsupervised learning for efficient motion segmentation

https://github.com/GiuliaDAngelo/Speckegomotion

공식 코드

Wandering around: A bioinspired approach to visual attention through object motion sensitivity

https://github.com/Jyxarthur/OCLR_model

공식 코드

Segmenting Moving Objects via an Object-Centric Layered Representation

https://github.com/Jyxarthur/flowsam

공식 코드

Moving Object Segmentation: All You Need Is SAM (and Flow)

https://github.com/TonyLianLong/RCF-UnsupVideoSeg

공식 코드

Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping

https://github.com/alex-xun-xu/MultiViewMoSeg

공식 코드

Motion Segmentation by Exploiting Complementary Geometric Models

https://github.com/anuragranj/cc

공식 코드

Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

https://github.com/aoki-media-lab/event_based_segmentation_vcmax

공식 코드

Iterative Event-based Motion Segmentation by Variational Contrast Maximization

https://github.com/bytedance/particle-sfm

공식 코드

ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild

https://github.com/cvgmi/nestedgrassmann

공식 코드

Nested Grassmannians for Dimensionality Reduction with Applications

https://github.com/danini/multi-x

공식 코드

Multi-Class Model Fitting by Energy Minimization and Mode-Seeking

https://github.com/dukebw/SSTVOS

공식 코드

SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation

https://github.com/federica-arrigoni/ICCV_19

공식 코드

Robust Motion Segmentation from Pairwise Matches

https://github.com/gengshan-y/rigidmask

공식 코드

Learning to Segment Rigid Motions from Two Frames

https://github.com/geniussh/dytanvo

공식 코드

DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments

https://github.com/hankuipeng/WSSR

공식 코드

Weighted Sparse Subspace Representation: A Unified Framework for Subspace Clustering, Constrained Clustering, and Active Learning

https://github.com/hkust-aerial-robotics/emsgc

공식 코드

Event-based Motion Segmentation with Spatio-Temporal Graph Cuts

https://github.com/huangjh-pub/multibody-sync

공식 코드

MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization

https://github.com/leolyliu/HOI4D-Instructions

공식 코드

HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction

https://github.com/ljacksonpan/ratrack

공식 코드

RaTrack: Moving Object Detection and Tracking with 4D Radar Point Cloud

https://github.com/mdimiccoli/gcrl-for-hms

공식 코드

Graph Constrained Data Representation Learning for Human Motion Segmentation

https://github.com/mfaisal59/EpONet

공식 코드

EpO-Net: Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency

https://github.com/mtangemann/common_fate_object_learning

공식 코드

Unsupervised Object Learning via Common Fate

https://github.com/o-vigia/gma3d

공식 코드

GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flow

https://github.com/panji1990/Low-rank-kernel-subspace-clustering

공식 코드

Adaptive Low-Rank Kernel Subspace Clustering

https://github.com/panji530/Robust-shape-interaction-matrix

공식 코드

Shape Interaction Matrix Revisited and Robustified: Efficient Subspace Clustering with Corrupted and Incomplete Data

https://github.com/prgumd/0-MMS

공식 코드

0-MMS: Zero-Shot Multi-Motion Segmentation With A Monocular Event Camera

https://github.com/rd20karim/M2T-Segmentation

공식 코드

Motion2Language, unsupervised learning of synchronized semantic motion segmentation

https://github.com/reeshadarian/RCUR

공식 코드

On Matrix Factorizations in Subspace Clustering

https://github.com/samiarja/ev_deep_motion_segmentation

공식 코드

Motion Segmentation for Neuromorphic Aerial Surveillance

https://github.com/sckangz/arctangent

공식 코드

Robust Subspace Clustering via Tighter Rank Approximation

https://github.com/sckangz/logdet

공식 코드

Robust Subspace Clustering via Smoothed Rank Approximation

https://github.com/scnu-rislab/cv-mos

공식 코드

CV-MOS: A Cross-View Model for Motion Segmentation

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.