AI Paper Atlas

Research map / 3D vision / Human pose estimation

Single-Scanline Relative Pose Estimation for Rolling Shutter Cameras

Petr Hruby, Marc Pollefeys

ICCV 2025 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 3 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 (D,3,7) instead of (E,3,5)rolling shutter relative pose, multi-view · Fastec (multi-view)% poses with error <= 10 deg: 1.0 % -> 5.6 %Improved
use (D,3,7) instead of (E,4,4)rolling shutter relative pose, multi-view · Fastec (multi-view, 19 sequences)sequences with error <= 5 deg: 5 -> 6Improved
use (E,4,4) instead of (E,3,5)rolling shutter relative pose, multi-view · Fastec (multi-view, 19 sequences)sequences with error <= 5 deg: 1 -> 5Improved
use (D,3,7) instead of (E,4,4)rolling shutter relative pose, multi-view · Fastec (multi-view)% poses with error <= 30 deg: 22.4 % -> 21.7 %Hurt
use single-view scanlines instead of multi-view images(D,3,7) · Fastecsequences with error <= 10 deg: 10 -> 4Hurt
use single-view scanlines instead of multi-view images(E,4,4) · Fastec% poses with error <= 30 deg: 22.4 % -> 10.0 %Hurt
use single-view scanlines instead of multi-view images(E,3,5) · Fastecsequences with error <= 20 deg: 10 -> 5Hurt

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