Robust Image Matching

Five questions. Choose one answer for each, then submit to see your score and explanations.

The practice target is 80%. You can retry as often as you like, and every lesson stays accessible.

You can practice as a guest. Sign in before starting an attempt to save your scores.

1. Which explanation matches filter descriptor matches?A. RANSAC repeatedly estimates a model from small samples and counts points that agree within a threshold.B. Estimate a suitable transform, warp one image, and blend their shared region.C. Nearest-match filtering and ratio-style comparisons can reject ambiguous descriptor candidates.D. A geometric check tests whether correspondences agree with the assumed transform throughout the scene.

2. Which explanation matches fit a transform with ransac?A. Nearest-match filtering and ratio-style comparisons can reject ambiguous descriptor candidates.B. RANSAC repeatedly estimates a model from small samples and counts points that agree within a threshold.C. Estimate a suitable transform, warp one image, and blend their shared region.D. A geometric check tests whether correspondences agree with the assumed transform throughout the scene.

3. Which explanation matches stitch images into a panorama?A. Estimate a suitable transform, warp one image, and blend their shared region.B. Nearest-match filtering and ratio-style comparisons can reject ambiguous descriptor candidates.C. RANSAC repeatedly estimates a model from small samples and counts points that agree within a threshold.D. A geometric check tests whether correspondences agree with the assumed transform throughout the scene.

4. For fit a transform with ransac, which result or action fits this practical case: A few false correspondences pull the fitted panorama sideways.A. Keep a distinct best match but question two almost equally close window matches.B. Check the alignment of corners before blending the seam.C. Inspect held-out foreground and background landmarks separately.D. Fit a transform from inlier matches while inspecting their spatial distribution.

5. For recognize when a match is geometrically wrong, which result or action fits this practical case: A stitched skyline looks plausible while the foreground doubles.A. Keep a distinct best match but question two almost equally close window matches.B. Fit a transform from inlier matches while inspecting their spatial distribution.C. Inspect held-out foreground and background landmarks separately.D. Check the alignment of corners before blending the seam.

Review this module from its first lesson →

Robust Image Matching

Your result