AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Renormalization for Initialization of Rolling Shutter Visual-Inertial Odometry

Branislav Mičušík, Georgios Evangelidis

IJCV 2021 · Architectures and efficiency › RNNs and normalization · approach: Dataset condensation and flow estimation · 2 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
replace least squares with renormalizationLS initializer · Rendered sequencesvelocity error: roughly 20%Improved
replace least squares with renormalizationLS initializer · Rendered sequencesgravity error: roughly 8%Improved
initialize BA with renormalization instead of LS (ablation)Bundle adjustment · Synthetic dataaccuracy and convergence speedMixed
use renormalization instead of Taubin or weighted LS (ablation)LS · Synthetic dataestimation errorImproved
add bundle adjustment ML refinement after renormalizationRenormalization · Synthetic dataestimation errorNo clear effect
model rolling shutter instead of global shutter camera (ablation)RNM · Synthetic dataestimation errorImproved
use stereo instead of monocular camera (ablation)LS, RNM, BA · Synthetic dataestimation errorImproved
use 4 frame pairs instead of 10 (ablation)RNM · Synthetic dataruntime: 3x speed-up for a small accuracy dropMixed
use 5 observations per 3D point instead of 8 (ablation)BA · Synthetic dataruntime: 1.2x speed-up for a small accuracy dropMixed
run 5 iterations of renormalization over Taubin (ablation)Taubin method · Synthetic dataestimation errorImproved

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