AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Learning Dual Convolutional Neural Networks for Low-Level Vision

Jinshan Pan, Sifei Liu, Deqing Sun, Jiawei Zhang, Yang Liu, Jimmy Ren, Zechao Li, Jinhui Tang, Huchuan Lu, Yu-Wing Tai, Ming-Hsuan Yang

CVPR 2018 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 209 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
jointly estimate structures and details with parallel branchesDualCNN · Super-resolution, Set5/Set14/Urban100/BSDS500PSNRImproved
use DualCNN instead of the strongest listed baseline, VDSRsuper-resolution · Set5 ×2PSNR: 37.6173 -> 37.7005Improved
use DualCNN instead of the strongest listed baseline, VDSRsuper-resolution · Set14 ×4PSNR: 28.0667 -> 28.0949Improved
use DualCNN instead of the strongest listed baseline, VDSRsuper-resolution · Urban100 ×4PSNR: 25.1575 -> 25.1722Improved
use DualCNN instead of the strongest listed baseline, VDSRsuper-resolution · BSDS500 ×4PSNR: 27.2342 -> 27.2454Improved
use DualCNN instead of VDSRimage filtering · WMFPSNR: 38.5 -> 39.1Improved
use DualCNN instead of VDSRimage filtering · RTVPSNR: 41.6 -> 42.1Improved
use DualCNN instead of Xu et al.image filtering · L0 smoothingPSNR: 32.8 -> 31.4Hurt
use DualCNN instead of ID-CGANderaining · synthetic rainy test datasetAvg. PSNR: 22.73 -> 24.11Improved
use DualCNN instead of Ren et al.dehazing · synthetic hazy image datasetAvg. PSNR: 18.38 -> 18.85Improved
add structure and detail branch regularization losses (ablation)DualCNN dehazing · dehazing validation dataAvg. PSNR: 21.13 -> 26.43Improved
use structure regularization only (ablation)DualCNN dehazing · dehazing validation dataAvg. PSNR: 21.13 -> 26.27Improved

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