Optical Flow MCQ 15 Questions
Time: ~25 mins Advanced

Optical Flow MCQ

Under brightness constancy, pixels appear to move—estimate (u,v) motion fields between frames.

Easy: 5 Q Medium: 6 Q Hard: 4 Q
Motion field

(u,v)

Constancy

I_t ≈ I_{t+1}

Aperture

Ambiguity

Smoothness

Regularize

Optical flow basics

Optical flow assigns a 2D displacement to each pixel between frames. Brightness constancy assumes pixel intensity is preserved along motion; combined with spatial smoothness (Horn–Schunck) or local linearization (Lucas–Kanade), it yields estimators. Deep networks now predict dense flow end-to-end (FlowNet, RAFT).

Aperture problem

Along a 1D edge, only the normal component of flow is observable locally—additional constraints resolve ambiguity.

Key ideas

Brightness constancy

I_x u + I_y v + I_t ≈ 0 (first-order).

Lucas–Kanade

Least squares on a patch assuming constant (u,v).

Horn–Schunck

Global smoothness regularizer + data term.

Deep flow

CNNs regress flow from image pairs directly.

From two frames

warp frame2 toward frame1 using estimated flow; minimize photometric error

Pro tip: Large displacements need pyramids (coarse-to-fine) or iterative refinement (e.g. RAFT).