Optical Flow Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 10
- 보존된 평가 기록
- 133
Optical Flow Estimation is a computer vision task that involves computing the motion of objects in an image or a video sequence. The goal of optical flow estimation is to determine the movement of pixels or features in the image, which can be used for various applications such as object tracking, motion analysis, and video compression.
Approaches for optical flow estimation include correlation-based, block-matching, feature tracking, energy-based, and more recently gradient-based.
Further readings:
Definition source: Devon: Deformable Volume Network for Learning Optical Flow
Image credit: Optical Flow Estimation
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Hardware, Algorithms, and Applications of the Neuromorphic Vision Sensor: a Review
Extending Visual Dynamics for Video-to-Music Generation
Beyond the Frame: Generating 360° Panoramic Videos from Perspective Videos
ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation
Saliency-Motion Guided Trunk-Collateral Network for Unsupervised Video Object Segmentation
Towards Efficient Real-Time Video Motion Transfer via Generative Time Series Modeling
FluentLip: A Phonemes-Based Two-stage Approach for Audio-Driven Lip Synthesis with Optical Flow Consistency
Simultaneous Motion And Noise Estimation with Event Cameras
Easi3R: Estimating Disentangled Motion from DUSt3R Without Training
ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation with Zero-Shot Method
Towards Mobile Sensing with Event Cameras on High-agility Resource-constrained Devices: A Survey
Synergistic Bleeding Region and Point Detection in Surgical Videos
Segment Any Motion in Videos
Endo-TTAP: Robust Endoscopic Tissue Tracking via Multi-Facet Guided Attention and Hybrid Flow-point Supervision
Can Video Diffusion Model Reconstruct 4D Geometry?
VADMamba: Exploring State Space Models for Fast Video Anomaly Detection
Burst Image Super-Resolution with Mamba
NexusGS: Sparse View Synthesis with Epipolar Depth Priors in 3D Gaussian Splatting
MotionDiff: Training-free Zero-shot Interactive Motion Editing via Flow-assisted Multi-view Diffusion
Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras
Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks
EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation
4D Gaussian Splatting SLAM
Temporal-Consistent Video Restoration with Pre-trained Diffusion Models
DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework
GeoFlow-SLAM: A Robust Tightly-Coupled RGBD-Inertial Fusion SLAM for Dynamic Legged Robotics
UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking Neural Networks
Zero-TIG: Temporal Consistency-Aware Zero-Shot Illumination-Guided Low-light Video Enhancement
FG-DFPN: Flow Guided Deformable Frame Prediction Network
EMoTive: Event-guided Trajectory Modeling for 3D Motion Estimation
ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
ST-FlowNet: An Efficient Spiking Neural Network for Event-Based Optical Flow Estimation
Markerless Tracking-Based Registration for Medical Image Motion Correction
Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations
Investigation of Frame Differences as Motion Cues for Video Object Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.