AI Paper Atlas

Research map / 3D vision / Depth and stereo

Camera Pose Estimation Using Implicit Distortion Models

Linfei Pan, Marc Pollefeys, Viktor Larsson

CVPR 2022 · 3D vision › Depth and stereo · approach: Camera model and calibration for SfM · 8 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Jointly optimize poses across multiple images using the implicit distortion modelCamera pose estimation · Structure-from-Motion: Kirchenge, Grossmunster, Kazan, Doge Palaceposition error: Kirchenge: 0.6 -> 0.4; Grossmunster: 0.9 -> 0.5; Kazan: 8.7 -> 3.4; Doge Palace: 3.4 -> 3.4Improved
Jointly optimize multiple images rather than estimate each image independentlyImplicit distortion model · Aachen Day-Night and InLoclocalized images (%): Aachen day: 58.3 / 76.5 / 94.2 -> 82.6 / 92.4 / 98.3; night: 61.2 / 77.6 / 99.0 -> 73.5 / 88.8 / 100.0; InLoc duc1: 28.3Improved
Apply the proposed implicit calibration and pose estimationVisual localization · Aachen Day-Night and InLoclocalized images (%): Aachen day: 82.6 / 92.4 / 98.3 vs 89.6 / 95.4 / 98.8; InLoc duc1: 34.8 / 52.5 / 69.7 vs 46.5 / 66.2 / 78.3Mixed
Filter spurious inliers (ablation)Proposed implicit distortion model · Aachen Day-Nightlocalized images (%): day: 77.8 / 90.8 / 98.3 -> 82.6 / 92.4 / 98.3; night: 73.5 / 88.8 / 100.0 -> 73.5 / 88.8 / 100.0Improved
Filter spurious inliers (ablation)Proposed implicit distortion model · InLoclocalized images (%): duc1: 35.4 / 53.0 / 69.7 -> 34.8 / 52.5 / 69.7; duc2: 35.9 / 58.0 / 74.0 -> 38.9 / 57.3 / 74.0Mixed
Use adjacent-point differences instead of local linear fitting (ablation)Implicit distortion regularizer · Checkerboard calibration test setsmean RMS reprojection error (px): 0.847 -> 6.881Hurt
Fit a quadratic rather than a linear local function (ablation)Implicit distortion regularizer · Checkerboard calibration test setsmean RMS reprojection error (px): 0.847 -> 1.208Hurt
Use 2 rather than 4 neighboring points (ablation)Implicit distortion regularizer · Checkerboard calibration test setsmean RMS reprojection error (px): 0.847 -> 0.881Hurt
Use 6 rather than 4 neighboring points (ablation)Implicit distortion regularizer · Checkerboard calibration test setsmean RMS reprojection error (px): 0.847 -> 0.839Improved
Use 8 rather than 4 neighboring points (ablation)Implicit distortion regularizer · Checkerboard calibration test setsmean RMS reprojection error (px): 0.847 -> 0.841Improved
Use 10 rather than 4 neighboring points (ablation)Implicit distortion regularizer · Checkerboard calibration test setsmean RMS reprojection error (px): 0.847 -> 0.842Improved
Use ℓ2 rather than Huber loss (ablation)Implicit distortion regularizer · Checkerboard calibration test setsmean RMS reprojection error (px): 0.847 -> 0.853Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy