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.
Channel-wise Motion Features for Efficient Motion Segmentation
Temporal Rate Reduction Clustering for Human Motion Segmentation
KDMOS:Knowledge Distillation for Motion Segmentation
FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity
EV-LayerSegNet: Self-supervised Motion Segmentation using Event Cameras
Event-based Egocentric Human Pose Estimation in Dynamic Environment
Iterative Event-based Motion Segmentation by Variational Contrast Maximization
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction
BEVMOSNet: Multimodal Fusion for BEV Moving Object Segmentation
Wandering around: A bioinspired approach to visual attention through object motion sensitivity
On Moving Object Segmentation from Monocular Video with Transformers
RoMo: Robust Motion Segmentation Improves Structure from Motion
DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild
Human Insights Driven Latent Space for Different Driving Perspectives: A Unified Encoder for Efficient Multi-Task Inference
CV-MOS: A Cross-View Model for Motion Segmentation
Retina-Inspired Object Motion Segmentation for Event-Cameras
Hardware-Algorithm Re-engineering of Retinal Circuit for Intelligent Object Motion Segmentation
Dense Monocular Motion Segmentation Using Optical Flow and Pseudo Depth Map: A Zero-Shot Approach
Motion Segmentation for Neuromorphic Aerial Surveillance
MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos
Zero-Shot Monocular Motion Segmentation in the Wild by Combining Deep Learning with Geometric Motion Model Fusion
Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence
Moving Object Segmentation: All You Need Is SAM (and Flow)
Neuromorphic Vision-based Motion Segmentation with Graph Transformer Neural Network
Out of the Room: Generalizing Event-Based Dynamic Motion Segmentation for Complex Scenes
A Unified Model Selection Technique for Spectral Clustering Based Motion Segmentation
WoodScape Motion Segmentation for Autonomous Driving -- CVPR 2023 OmniCV Workshop Challenge
Appearance-Based Refinement for Object-Centric Motion Segmentation
Un-EvMoSeg: Unsupervised Event-based Independent Motion Segmentation
Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes
Motion2Language, unsupervised learning of synchronized semantic motion segmentation
Segmenting the motion components of a video: A long-term unsupervised model
Motion Segmentation from a Moving Monocular Camera
RaTrack: Moving Object Detection and Tracking with 4D Radar Point Cloud
Joint Self-supervised Depth and Optical Flow Estimation towards Dynamic Objects
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.