← Back to curriculum

Module 2 — Geometry & correspondence

Module 2 quiz & review

20 interactive multiple-choice questions covering projection, features, RANSAC, and stereo with lesson review links.

~45 min read + exercises

Before we begin

Aim for at least 16 out of 20 before the panorama project.


Multiple choice quiz

Interactive quiz

Pick one answer per question. Feedback appears immediately — take your time before clicking.

0 / 20 correct·0 answered
  1. Question 1 of 20

    In the pinhole camera model, homogeneous coordinates allow us to:

    Answer options for question 1
  2. Question 2 of 20

    Camera intrinsic matrix K encodes:

    Answer options for question 2
  3. Question 3 of 20

    Harris corner detector looks for points where:

    Answer options for question 3
  4. Question 4 of 20

    Lowe's ratio test when matching SIFT descriptors rejects matches when:

    Answer options for question 4
  5. Question 5 of 20

    RANSAC is used in geometric vision primarily to:

    Answer options for question 5
  6. Question 6 of 20

    Radial lens distortion causes straight lines in the scene to:

    Answer options for question 6
  7. Question 7 of 20

    In rectified stereo, corresponding points lie:

    Answer options for question 7
  8. Question 8 of 20

    Depth Z from disparity d (baseline B, focal length f) scales as:

    Answer options for question 8
  9. Question 9 of 20

    A homography H maps points between two views when:

    Answer options for question 9
  10. Question 10 of 20

    ORB descriptors are popular in real-time pipelines because:

    Answer options for question 10
  11. Question 11 of 20

    Zhang's calibration method uses multiple views of a checkerboard to:

    Answer options for question 11
  12. Question 12 of 20

    Textureless regions are hard for stereo matching because:

    Answer options for question 12
  13. Question 13 of 20

    The essential matrix E relates corresponding points in:

    Answer options for question 13
  14. Question 14 of 20

    Scale-invariant feature detectors address the problem that:

    Answer options for question 14
  15. Question 15 of 20

    Wider stereo baseline generally:

    Answer options for question 15
  16. Question 16 of 20

    The principal point in K is:

    Answer options for question 16
  17. Question 17 of 20

    Increasing RANSAC iterations is needed when:

    Answer options for question 17
  18. Question 18 of 20

    Epipolar geometry constrains matching so that:

    Answer options for question 18
  19. Question 19 of 20

    Subpixel disparity refinement improves depth maps by:

    Answer options for question 19
  20. Question 20 of 20

    Reprojection error in calibration measures:

    Answer options for question 20

What's next

Project: panorama stitching