AI Paper Atlas

Research map / 3D vision / Human pose estimation

Equivalent Constraints for Two-View Geometry: Pose Solution/Pure Rotation Identification and 3D Reconstruction

Qi Cai, Yuanxin Wu, Lilian Zhang, Peike Zhang

IJCV 2018 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 27 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 the two-inequality pose identification instead of traditional reconstruction plus positive-depth checktwo-view pose solution selection · Simulation (d=30m, 50m, 80m)translation discrepancy difference: difference almost all above zeroImproved
use analytical depth reconstruction instead of DLT triangulation3D point reconstruction · Simulation, small parallax and large noisereconstruction error ratio: ratio much less than 1Improved
use analytical reconstruction instead of DLT triangulation at large parallax3D point reconstruction · Simulation, large parallaxreconstruction error ratioNo clear effect
use analytical reconstruction instead of traditional triangulation3D point reconstruction · Real barcode tests (21 view pairs)reconstruction error ratio: better for all pairs except the 3-4 pairImproved
initialize bundle adjustment with analytical instead of traditional reconstructionbundle adjustment · Real barcode tests, 1-4 view pairBA convergence: well-behaved BA vs diverging BAImproved
add bundle adjustment after analytical reconstructionanalytical reconstruction · Real barcode tests (21 view pairs)reconstruction error ratioNo clear effect
use PRI (Proposition 8) instead of the other rotation indicator for pure rotation identification (ablation)pure rotation identification · Simulation, d=30m, 50m, 80mthreshold separability: threshold 0.015 works for all depthsImproved
use inequality-based identification (Methods I and II) instead of traditional DLT with positive depth checkpose identification · Computation cost vs number of feature points (20 Monte Carlo runs)time cost: reduce the time cost by about 7-9 timesImproved

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