Stereo Vision MCQ 15 Questions
Time: ~25 mins Advanced

Stereo Vision MCQ

Correspondence, rectified scanlines, disparity maps, and turning two images into metric or relative depth.

Easy: 5 Q Medium: 6 Q Hard: 4 Q
Two views

Baseline

Disparity

Pixel shift

Matching

Cost volume

Depth map

Z(x,y)

Stereo vision in practice

Given two calibrated views, find pixel correspondences along epipolar lines (often after rectification), compute disparity, and recover depth via triangulation. Local methods (block matching, SAD/SSD) and global or learning-based matchers trade accuracy, speed, and occlusion handling.

Rectification

Warp both images so epipolar lines are horizontal scanlines—turns 2D search into 1D along rows.

Key ideas

Correspondence

For each pixel in the reference view, find the matching pixel in the second view.

Disparity

Horizontal shift d = x_left − x_right after rectification (sign convention varies).

Cost volume

Stores matching costs over disparities; winner-take-all or optimization (e.g. SGM).

Occlusions

Regions visible in only one image break uniqueness; often detected via consistency checks.

Stereo pipeline

Calibrate → rectify → match → disparity → depth → optional filtering / fusion

Pro tip: Textureless regions and repeated patterns cause ambiguity—regularization and multi-scale help.