AI Paper Atlas

Research map / 3D vision / Depth and stereo

Mirror Surface Reconstruction Under an Uncalibrated Camera

CVPR 2016 · 3D vision › Depth and stereo · approach: Camera model and calibration for SfM · 4 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use cross-ratio optimization instead of the linear solution (ablation)Mirror surface reconstruction · Stanford bunny, σ = 2.0 pixelsfocal length fu estimation error: 1.18% -> 0.14%Helped
Use cross-ratio optimization instead of the constrained linear solution (ablation)Mirror surface reconstruction · Stanford bunny, σ = 2.0 pixelsfocal length fu estimation error: 1.32% -> 0.14%Helped
Estimate plane poses rather than using calibrated plane poses (ablation)Mirror surface reconstruction · Sauce boatRMS reconstruction error: 2.55 -> 2.71Hurt
Estimate plane poses rather than using calibrated plane poses (ablation)Mirror surface reconstruction · Two spheresRMS reconstruction error: 1.78 -> 2.03Hurt
Use uncalibrated camera and plane poses instead of calibrated camera and plane posesMirror surface reconstruction · Sphere patchRMS reconstruction errorNo clear effect

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