AI Paper Atlas

Research map / Image generation / Image restoration

Multi-Scale Residual Low-Pass Filter Network for Image Deblurring

Jiangxin Dong, Jinshan Pan, Zhongbao Yang, Jinhui Tang

ICCV 2023 · Image generation › Image restoration · approach: Dehazing and deraining · 81 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 learnable self-attention low-pass filter (with wavelet fusion) (ablation)MRLPFNet · GoPro testPSNR (dB): 33.0 -> 33.5Improved
add learnable low-pass filter without feature fusion (ablation)MRLPFNet · GoPro testPSNR (dB): 32.8 -> 33.4Improved
replace bilinear feature fusion with wavelet-based fusion (ablation)MRLPFNet w/o LPF · GoPro testPSNR (dB): 32.9 -> 33.0Improved
add wavelet-based feature fusion on top of LPF (ablation)MRLPFNet · GoPro testPSNR (dB): 33.4 -> 33.5Improved
add bilinear feature fusion with no LPF (ablation)MRLPFNet w/o LPF · GoPro testPSNR (dB): 32.8 -> 32.9Improved
add learnable low-pass filter (self-attention) (ablation)MRLPFNet · Model complexityRunning time (s): 0.2613 -> 0.8633Hurt
increase RLPF modules per block from 8 to 20 (MRLPFNet-L)MRLPFNet · GoPro testPSNR (dB): 33.50 -> 34.01Improved

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