AI Paper Atlas

Research map / Video / Video segmentation and tracking

Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training

Dongwon Park, Dong Un Kang, Jisoo Kim, Se Young Chun

ECCV 2020 · Video › Video segmentation and tracking · approach: Spike and neuromorphic deblurring · 269 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 kernel size 3 instead of 5 (ablation)MS network of Tao · GoPro (ablation, intermediate-TL dataset)PSNR (dB): 29.97 -> 30.10Improved
add residual learning (ablation)MS network · GoPro (ablation, intermediate-TL dataset)PSNR (dB): 30.10 -> 30.25Improved
add residual skip connection linked with I0 (ablation)MT-RNN · GoPro with intermediate TL imagesPSNR (dB): 0.15dBImproved
replace multi-scale with multi-temporal approach (ablation)Tao-style network, K=3, residual · GoPro (ablation, intermediate-TL dataset)PSNR (dB): 30.25 -> 30.43Improved
add recurrent feature maps (ablation)MT-RNN · GoPro (ablation, intermediate-TL dataset)PSNR (dB): 30.43 -> 30.74Improved
combine MS with MT instead of MT alone (ablation)MT-RNN · GoPro (ablation, intermediate-TL dataset)PSNR (dB): 30.74 -> 30.58Hurt
use 2 temporal steps instead of one-stage (0 steps) (ablation)MT-RNN · GoPro (temporal steps and size ablation)PSNR (dB): 29.93 -> 30.74Improved
use temporal step 4 instead of 2 (ablation)MT-RNN · GoPro (temporal steps and size ablation)PSNR (dB): 30.74 -> 30.44Hurt
halve parameter size (1.46M vs 2.63M) (ablation)MT-RNN · GoPro (temporal steps and size ablation)PSNR (dB): 30.74 -> 30.21Hurt
double parameter size (5.35M vs 2.63M) (ablation)MT-RNN · GoPro (temporal steps and size ablation)PSNR (dB): 30.74 -> 30.84No clear effect
apply MT approach with incremental temporal training (ablation)Zhang network · GoProPSNR (dB): 30.25 -> 30.91Improved
apply MT approach with incremental temporal training (ablation)Kupyn network · GoProPSNR (dB): 28.27 -> 28.36No clear effect

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