AI Paper Atlas

Research map / 3D vision / Depth and stereo

Robust and Globally Optimal Manhattan Frame Estimation in Near Real Time

Kyungdon Joo, Tae-Hyun Oh, Junsik Kim, In So Kweon

TPAMI 2018 · 3D vision › Depth and stereo · approach: Camera model and calibration for SfM · 35 citations (OpenAlex)

Read the paperCheck 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
use EGI-based relaxed bound instead of exhaustive bound computationbranch-and-bound MF estimation · synthetic databound computation time: 108.178s -> 4.6msImproved
use EGI-based relaxed bound instead of exhaustive BnBbranch-and-bound MF estimation · NYUv2runtime: 117.06 -> 0.07Improved
relax the problem on the EGI instead of solving the exact problembranch-and-bound MF estimation · NYUv2average angular error: 2.5 -> 2.63Hurt
use proposed BnB instead of RMFEMF estimation · NYUv2average angular error: 3.27 -> 2.63Improved
use proposed BnB instead of MMFMF estimation · NYUv2average angular error: 5.07 -> 2.63Improved
use proposed BnB instead of RTMF with IMU fusionMF estimation · sequence datasetangular RMSE: 3.05 -> 1.53Improved
use proposed BnB instead of vMF-RTMF aloneMF estimation · sequence datasetangular RMSE: 6.39 -> 1.53Improved
increase EGI resolution parameter s (ablation)proposed BnB · synthetic dataangular error and runtimeMixed
vary inlier threshold tau (ablation)proposed BnB · synthetic dataangular errorNo clear effect
use proposed method instead of MMF for two MFsmultiple MF estimation · NYUv2 multiple MFtheta_x angular error: 13.8 -> 6.3Improved
use proposed method instead of MMF for one MFmultiple MF estimation · NYUv2 multiple MFtheta_x angular error: 5.2 -> 2.8Improved
use proposed method instead of RMFE for VP estimationVP estimation · York Urban Datasethorizon-error AUC: 77.62% -> 82.56%Improved

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