RAFT computes dense optical flow with high accuracy by iteratively refining its estimate, handling large and complex motion better than older equation-based methods. It is the go-to when flow quality matters more than the lightest possible compute.
Definition
A deep-learning optical-flow model that is accurate on hard motion. The modern default when classical methods like Lucas-Kanade are not precise enough.
RAFT computes dense optical flow with high accuracy by iteratively refining its estimate, handling large and complex motion better than older equation-based methods. It is the go-to when flow quality matters more than the lightest possible compute.
Also known as
Lucas-Kanade
Specialist software house for video, real-time and AI products. Founded 2005. 50 in-house engineers.
