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.
Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow
MambaFlow: A Mamba-Centric Architecture for End-to-End Optical Flow Estimation
Online Dense Point Tracking with Streaming Memory
Stereo Any Video: Temporally Consistent Stereo Matching
VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
ReynoldsFlow: Exquisite Flow Estimation via Reynolds Transport Theorem
BAT: Learning Event-based Optical Flow with Bidirectional Adaptive Temporal Correlation
Anomaly detection in non-stationary videos using time-recursive differencing network based prediction
AI-Driven Relocation Tracking in Dynamic Kitchen Environments
EVLoc: Event-based Visual Localization in LiDAR Maps via Event-Depth Registration
Learning Temporal 3D Semantic Scene Completion via Optical Flow Guidance
Task-Oriented Semantic Communication for Stereo-Vision 3D Object Detection
L4P: Low-Level 4D Vision Perception Unified
Stonefish: Supporting Machine Learning Research in Marine Robotics
Robust 6DoF Pose Tracking Considering Contour and Interior Correspondence Uncertainty for AR Assembly Guidance
Learning semantical dynamics and spatiotemporal collaboration for human pose estimation in video
Super Resolution image reconstructs via total variation-based image deconvolution: a majorization-minimization approach
FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis
Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors
A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision
A Physical Coherence Benchmark for Evaluating Video Generation Models via Optical Flow-guided Frame Prediction
MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent
XR-VIO: High-precision Visual Inertial Odometry with Fast Initialization for XR Applications
REMOTE: Real-time Ego-motion Tracking for Various Endoscopes via Multimodal Visual Feature Learning
Extending Information Bottleneck Attribution to Video Sequences
Improved Encoding for Overfitted Video Codecs
Image Velocimetry using Direct Displacement Field estimation with Neural Networks for Fluids
TranStable: Towards Robust Pixel-level Online Video Stabilization by Jointing Transformer and CNN
GC-ConsFlow: Leveraging Optical Flow Residuals and Global Context for Robust Deepfake Detection
Machine Learning Modeling for Multi-order Human Visual Motion Processing
MONA: Moving Object Detection from Videos Shot by Dynamic Camera
VipDiff: Towards Coherent and Diverse Video Inpainting via Training-free Denoising Diffusion Models
Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
Learning segmentation from point trajectories
Event-based vision for egomotion estimation using precise event timing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.