AI Paper Atlas

Research map / 3D vision / Depth and stereo

High-Quality Depth From Uncalibrated Small Motion Clip

CVPR 2016 · 3D vision › Depth and stereo · approach: Camera model and calibration for SfM · 99 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 intensity-profile variance instead of pairwise SAD for plane-sweeping matching (ablation)Dense stereo matching · Synthetic clip (b = −2.1, n = 31)MAD: 8.650 -> 5.763Helped
Use intensity-profile variance instead of pairwise SAD for plane-sweeping matching (ablation)Dense stereo matching · Synthetic clip (b = −2.1, n = 31)R5: 64.940 -> 67.728Helped
Use intensity-profile variance instead of pairwise SAD for plane-sweeping matching (ablation)Dense stereo matching · Synthetic clip (b = −2.1, n = 31)R10: 86.419 -> 90.201Helped
Estimate focal length and radial distortion jointly with camera poses and scene pointsSmall-motion bundle adjustment · Small-motion camera clipsdistortion error (pixel): 5.76 -> 0.52; 5.89 -> 0.53; 3.65 -> 1.48; 3.25 -> 1.14Helped
Use more than 30 frames and a baseline greater than 1% of the nearest scene depthProposed depth reconstruction · Synthetic small-motion clipsR5: around 80%Helped

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