AI Glossary

Optical Flow

The pattern of apparent motion of objects between consecutive video frames.

Overview

Optical flow describes the apparent motion of pixels or features between consecutive frames in a video sequence. It produces a vector field where each vector represents the displacement of a point from one frame to the next, providing information about the spatial arrangement and motion of objects in the scene.

Key Details

Modern optical flow estimation uses deep learning (FlowNet, RAFT, PWC-Net) to predict dense motion fields. Applications include video stabilization, action recognition, autonomous driving, video interpolation, and object tracking. Optical flow is also used in text-to-video generation models to ensure temporal consistency.

Related Concepts

computer visionobject detectiondepth estimation

← Back to AI Glossary

Last updated: March 5, 2026