AI Paper Atlas

Research map / Video / Video segmentation and tracking

Event-Based Motion Deblurring Using Task-Oriented 3D Gaussian Event Representations

Shengdong Xue, Haoxiang Ma, Hao Chen, Zhen Yang, Yongjian Deng

CVPR 2026 · Video › Video segmentation and tracking · approach: Event-based video reconstruction

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 Voxel Grid with learnable 3D Gaussian event representation (ablation)deblurring network · GoProPSNR (dB): 36.13 -> 36.51Improved
add blur-map prior (ablation)3D-GSER network · GoProPSNR (dB): 36.51 -> 36.61Improved
add bidirectional attention fusion (BAF) (ablation)3D-GSER network · GoProPSNR (dB): 36.51 -> 36.76Improved
combine blur map and BAF (ablation)3D-GSER network · GoProPSNR (dB): 36.51 -> 36.86Improved
add full modules on REBlur (ablation)3D-GSER network · REBlurPSNR (dB): 38.01 -> 38.68Improved
use learning-based EST instead of Voxel Grid (ablation)deblurring network · GoProPSNR (dB): 36.13 -> 35.86Hurt
use handcrafted SCER instead of Voxel Grid (ablation)deblurring network · GoProPSNR (dB): 36.13 -> 35.95Hurt
proposed method vs best prior on HS-ERGBfull method · HS-ERGBPSNR (dB): 27.93 -> 28.55Improved
proposed method vs best prior on GoPro (SSIM)full method · GoProSSIM: 0.979 (EIFNet) vs 0.977Mixed

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