AI Paper Atlas

Research map / Image generation / Editing and style transfer

ERL-Net: Entangled Representation Learning for Single Image De-Raining

Guoqing Wang, Changming Sun, Arcot Sowmya

ICCV 2019 · Image generation › Editing and style transfer · approach: Image-to-image translation · 82 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 skip-connections to the encoder-decoder de-raining model (ablation)MEMD · Rain100HPSNR: 24.0743 -> 29.3782Improved
add skip-connections to the encoder-decoder de-raining model (ablation)MEMD · AGAN-Data (raindrop)PSNR: 30.4712 -> 31.4305Improved
add the feature fusion layer after skip-connections (ablation)MEMD · Rain100HPSNR: 29.3782 -> 31.6310Improved
add the feature fusion layer after skip-connections (ablation)MEMD · AGAN-Data (raindrop)PSNR: 31.4305 -> 32.2139Improved
add the entangled residual encoder branch (MA D + MLGD)MEMD · Rain100HPSNR: 31.6310 -> 34.5724Improved
add the entangled residual encoder branch (MA D + MLGD)MEMD · AGAN-Data (raindrop)PSNR: 32.2139 -> 32.9647Improved
use multiple layer guided entanglement (MLGD) instead of middle-layer only (CLGD) (ablation)ERL-Net MA D · Rain100HPSNR: 33.0145 -> 34.5724Improved
use multiple layer guided entanglement (MLGD) instead of middle-layer only (CLGD) (ablation)ERL-Net MA D · AGAN-Data (raindrop)PSNR: 32.7124 -> 32.9647Improved
use stage-wise training (MA D) instead of direct one-stage training (ablation)ERL-Net MLGD · Rain100HPSNR: 31.6287 -> 34.5724Improved
use direct training of the residual branch without pre-training (ablation)MEMD plus residual branch · Rain100HPSNR: 31.6310 -> 31.6214No clear effect
add a third stage fine-tuning MDE with the pixel loss (MA C vs MA A) (ablation)ERL-Net MLGD · Rain100HPSNR: 31.6804 -> 33.2041Improved
fine-tune REN and MDE jointly in stage 3 instead of MDE only (MA D vs MA C) (ablation)ERL-Net MLGD · Rain100HPSNR: 33.2041 -> 34.5724Improved

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