AI Paper Atlas

Research map / Detection and segmentation / CNN features

Generative Status Estimation and Information Decoupling for Image Rain Removal

Di Lin, Xin WANG, Jia Shen, Renjie Zhang, Ruonan Liu, Miaohui Wang, Wuyuan Xie, Qing Guo, Ping Li

NeurIPS 2022 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 0 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
increase number of generated kernels N from 1 to 8 (ablation)SEIDNet · Rain100HPSNR: 31.457 -> 33.217Improved
increase kernels from N=8 to 32 (ablation)SEIDNet · Rain100HPSNR: 33.217 -> 33.221No clear effect
replace both discriminative networks with CVAEs (status estimation and information decoupling) (ablation)SEIDNet · Rain100HPSNR: 29.43 -> 33.22Improved
use CVAE only for status estimation (ablation)discriminative baseline · Rain100HPSNR: 29.43 -> 29.62Improved
use CVAE only for information decoupling (ablation)discriminative baseline · Rain100HPSNR: 29.43 -> 31.42Improved
use generative CVAE instead of discriminative network for kernel estimation (ablation)SEIDNet · Rain100HPSNR: 29.91 -> 33.22Improved
average discriminative and generative kernel maps (ablation)SEIDNet · Rain100HPSNR: 33.22 -> 33.11Hurt
two factorized CVAEs for (K, R) instead of one CVAE for (K, R) (ablation)SEIDNet · Rain100HPSNR: 29.03 -> 33.22Improved
add status map conditioning (versus single CVAE for K only) (ablation)SEIDNet · Rain100HPSNR: 25.21 -> 33.22Improved
train with only 1K random SPA images (subset A)SEIDNet vs MPR · SPA subset APSNR: 35.57 -> 39.07Improved
SEIDNet vs best prior on Rain100HSPDNet · Rain100HPSNR: 32.68 -> 33.22Improved
SEIDNet on desnowing vs DDMSNetDDMSNet · Snow100K OverallPSNR: 32.03 -> 32.77Improved

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