AI Paper Atlas

Research map / Video / Video segmentation and tracking

Progressive Spatio-Temporal Alignment for Efficient Event-Based Motion Estimation

Xueyan Huang, Yueyi Zhang, Zhiwei Xiong

CVPR 2023 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 25 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 progressive event-to-map alignment with the proposed time-surface lossevent-based rotational motion estimation · Event-Camera datasetRMSw: poster rotation: 11.67 -> 9.98; dynamic rotation: 6.40 -> 4.78; shapes rotation: 48.90 -> 10.62; classroom: 5.19 -> 2.61Improved
use progressive event-to-map alignment with the proposed time-surface lossevent-based homography motion estimation · poster sequences: translation, 6dof, hdrRMSw: translation: 17.14 -> 13.28; 6dof: 51.47 -> 22.54; hdr: 22.08 -> 17.08Improved
use progressive event-to-map alignment with the proposed time-surface lossevent-based 6-DOF motion estimation · MVSEC indoor flying1 and outdoor driving1RMSw: indoor flying1: 1.38 -> 1.05; outdoor driving1: 4.00 -> 2.72Improved
increase sampled events from 0.1k to 1k to 10k to 30k (ablation)progressive alignment · poster rotationRMSw: 10.23 -> 10.11 -> 9.99 -> 9.98Improved
increase sampled events from 0.1k to 1k to 10k to 30k (ablation)progressive alignment · shapes rotationRMSw: 10.92 -> 10.85 -> 10.55 -> 10.62Mixed
add bidirectional warping instead of using unidirectional warping (ablation)Ours-30k with dynamic batches · poster rotationRMSw: 11.05 -> 9.98Improved
add bidirectional warping instead of using unidirectional warping (ablation)Ours-30k with dynamic batches · shapes rotationRMSw: 15.08 -> 10.62Improved
use dynamic rather than fixed-size batches (ablation)Ours-30k with bidirectional warping · poster rotationRMSw: 10.21 -> 9.98Improved
use dynamic rather than fixed-size batches (ablation)Ours-30k with bidirectional warping · shapes rotationRMSw: 18.39 -> 10.62Improved
use bidirectional warping and dynamic batches rather than unidirectional warping and fixed-size batches (ablation)Ours-30k · poster rotationRMSw: 11.10 -> 9.98Improved
use bidirectional warping and dynamic batches rather than unidirectional warping and fixed-size batches (ablation)Ours-30k · shapes rotationRMSw: 22.41 -> 10.62Improved
use bidirectional rather than unidirectional warping (ablation)Ours-30k with dynamic batches · poster rotationTime: 15.9 -> 35.7Hurt

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