AI Paper Atlas

Research map / Video / Video segmentation and tracking

Event-based Mosaicing Bundle Adjustment

Shuang Guo, Guillermo Gallego

ECCV 2024 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 6 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
refine CMax-omega rotations with EMBACMax-omega · Synthetic townrotation RMSE (deg): 1.905 -> 0.858Improved
refine CMax-omega with EMBACMax-omega · Synthetic cityrotation RMSE (deg): 1.532 -> 0.973Improved
refine EKF-SMT with EMBAEKF-SMT · Synthetic sequencesrotation RMSE (deg): playroom 5.861 -> 6.094; bicycle 1.466 -> 1.182Mixed
refine front-end with EMBACMax-omega · Synthetic playroomsquared photometric error (x10^6): 0.326 -> 0.151Improved
refine front-end rotations with EMBA on real dataRTPT, CMax-GAE, CMax-omega · ECD real sequencesphotometric error: around 30% to 50% reductionImproved
refine front-end rotations with EMBA on real dataRTPT · ECD shapes (real)rotation RMSE (deg): 2.187 -> 2.85Hurt
initialize EMBA with CMax-SLAMCMax-SLAM · Street sceneARE (deg): 0.470 -> 0.377Improved
use Schur solver exploiting block-diagonal sparsity instead of CG (ablation)EMBA · ECD runtimetime solving normal equations (s): poster 3.127 -> 2.013; shapes 0.267 -> 0.429Mixed

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