AI Paper Atlas

Research map / Video / Video segmentation and tracking

REDIR: Refocus-free Event-based De-occlusion Image Reconstruction

Qi Guo, Hailong Shi, Huan Li, Jinsheng Xiao, Xingyu Gao

ECCV 2024 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 1 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
add STN alignment to UNet+Hybrid (with PMCM and TSA) (ablation)REDIR · E-SAI (part)PSNR: 31.07 -> 32.61Improved
add perceptual mask-gated connection module PMCM (ablation)REDIR · E-SAI (part)PSNR: 32.34 -> 32.61Improved
add spatial-temporal attention TSA in SNN block (ablation)REDIR · E-SAI (part)SSIM: 0.8232 -> 0.8842Improved
add UNet front end to Hybrid (ablation)Hybrid · E-SAI (part)PSNR: 23.32 -> 26.45Improved
REDIR (no prior) versus Refocus+Hybrid that needs manual refocusingE-SAI total · E-SAI totalPSNR: 27.94 -> 25.74Hurt
REDIR versus Hybrid without prior informationE-SAI total · E-SAI totalPSNR: 22.32 -> 25.74Improved
pretrain Refocus+Hybrid on dataset without prior informationRefocus+Hybrid · E-SAI without prior informationreconstructionHurt

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