AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Human-Aware Motion Deblurring

Ziyi Shen, Wenguan Wang, Xiankai Lu, Jianbing Shen, Haibin Ling, Tingfa Xu, Ling Shao

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 368 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 the human-aware attention module (ablation)Human-aware deblurring model · GoPro testPSNR: 29.30 -> 30.26Improved
add the human-aware attention module (ablation)Human-aware deblurring model · HIDE I testPSNR: 28.40 -> 29.60Improved
add the human-aware attention module (ablation)Human-aware deblurring model · HIDE II testPSNR: 27.58 -> 28.12Improved
add multi-head decoder blending (main branch fusing FG and BG) instead of FG branch only (ablation)Human-aware deblurring model · GoPro testPSNR: 29.59 -> 30.26Improved
add multi-head decoder blending (main branch fusing FG and BG) instead of FG branch only (ablation)Human-aware deblurring model · HIDE I testPSNR: 28.59 -> 29.60Improved
add multi-head decoder blending (main branch fusing FG and BG) instead of FG branch only (ablation)Human-aware deblurring model · HIDE II testPSNR: 27.55 -> 28.12Improved
add multi-head decoder blending instead of BG branch only (ablation)Human-aware deblurring model · GoPro testPSNR: 29.78 -> 30.26Improved
add multi-head decoder blending instead of BG branch only (ablation)Human-aware deblurring model · HIDE I testPSNR: 28.89 -> 29.60Improved
add multi-head decoder blending instead of BG branch only (ablation)Human-aware deblurring model · HIDE II testPSNR: 27.68 -> 28.12Improved
use multi-scale instead of single-scale (ablation)Human-aware deblurring model · GoPro testPSNR: 29.85 -> 30.26Improved
use multi-scale instead of single-scale (ablation)Human-aware deblurring model · HIDE I testPSNR: 28.47 -> 29.60Improved
use multi-scale instead of single-scale (ablation)Human-aware deblurring model · HIDE II testPSNR: 27.81 -> 28.12Improved

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