AI Paper Atlas

Research map / Video / Video segmentation and tracking

Motion Aware Event Representation-driven Image Deblurring

Zhijing Sun, Xueyang Fu, Longzhuo Huang, Aiping Liu, Zheng-Jun Zha

ECCV 2024 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 21 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 deviation accumulation (DA) event representation instead of best alternative (SCER) (ablation)event-based deblurring network · GoProPSNR: 35.81 -> 36.07Improved
use stack representation instead of DA (ablation)event-based deblurring network · GoProPSNR: 36.07 -> 33.24Hurt
add recurrent motion extraction (RME) module instead of a conv block (ablation)event-based deblurring network · GoProPSNR: 35.42 -> 36.07Improved
use FAF alignment-and-fusion instead of cross-modality attention (ablation)event-based deblurring network · GoProPSNR: 35.75 -> 36.07Improved
use FAF instead of direct concatenation (ablation)event-based deblurring network · GoProPSNR: 34.02 -> 36.07Improved
bi-directional alignment instead of aligning only one modality (ablation)FAF module · GoProPSNR: 35.78 -> 36.07Improved
add DA event representation to image-only HINetHINet · GoProPSNR: 32.71 -> 34.63Improved
add DA event representation to image-only UFPNetUFPNet · GoProPSNR: 34.06 -> 35.22Improved

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