AI Paper Atlas

Research map / 3D vision / Human pose estimation

Relative Pose from Deep Learned Depth and a Single Affine Correspondence

Ivan Eichhardt, Daniel Barath

ECCV 2020 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 20 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 1AC+D instead of 5PT in RANSACGC-RANSAC · 1DSfM relative poseprocessing timeImproved
use 1AC+D instead of 5PT in RANSACGC-RANSAC · 1DSfM relative poserotation and translation errorNo clear effect
use 1AC+D instead of 5PT as pose-graph initializerTheia global SfM · 1DSfMaccuracy and runtimeNo clear effect
use 1AC+D instead of 5PT as pose-graph initializerTheia global SfM · Vienna Cathedralruntime (s): 81,4 -> 56,5Improved
use 1AC+D instead of 5PT as pose-graph initializerTheia global SfM · Madrid Metropolisorientation AVG error: 6,9 -> 5,2Improved
use 1AC+D instead of 5PT as pose-graph initializerTheia global SfM · NYC Libraryruntime (s): 5,9 -> 10,4Hurt
use 1AC+D instead of 5PT as pose-graph initializerTheia global SfM · Ellis Islandorientation AVG error: 3,1 -> 4,4Hurt
compute rotation by the proposed algorithm instead of SVD or Gram-Schmidt1AC+D · relative posespeedImproved
use 1AC+D (proposed) instead of Umeyama alignment1AC+D · solver complexityoperations per iteration: 345 -> 133Improved

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