AI Paper Atlas

Research map / Image generation / GANs

Re-Boosting Self-Collaboration Parallel Prompt GAN for Unsupervised Image Restoration

Xin Lin, Yuyan Zhou, Jingtong Yue, Chao Ren, Kelvin C. K. Chan, Lu Qi, Ming-Hsuan Yang

TPAMI 2025 · Image generation › GANs · approach: GAN-based image manipulation · 20 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 BGM loss to unpaired GAN denoiser (V1 to V2) (ablation)V1 · SIDD denoising ablationPSNR: 34.52 -> 34.69Improved
add PL module (V2 to V3) (ablation)V2 · SIDD denoising ablationPSNR: 34.69 -> 34.92Improved
add self-synthesis constraint (V3 to V4) (ablation)V3 · SIDD denoising ablationPSNR: 34.92 -> 35.37Improved
use parallel two-branch P2GAN instead of V4 (ablation)V4 SGabNet · SIDD denoising ablationPSNR: 35.37 -> 35.90Improved
add self-collaboration iterations (ablation)P2GAN · SIDD ValidationPSNR: gains exceeding 0.5 dB in the first iteration; final iteration only about 0.03 dBImproved
add Reb-SC stage after SC converges (ablation)SCP2GAN · SIDD Validation and Rain100LPSNR: approximately 0.3 dBImproved
add SC and Reb-SC (full RSCP2GAN) to P2GAN (ablation)P2GAN · SIDD Validation and Rain100LPSNR: 1.93 dB on the SIDD Validation and 1.95 dB on Rain100LImproved
Reb-SC with N=2 augmentations vs none (ablation)Reb-SC · SIDD ValidationPSNR: 37.51 -> 37.71Improved
Reb-SC with N=4 augmentations vs none (ablation)Reb-SC · SIDD ValidationPSNR: 37.51 -> 37.83Improved
increase Reb-SC augmentations from N=4 to N=8 (ablation)Reb-SC · SIDD ValidationPSNR: 37.83 -> 37.78No clear effect
apply SC to DnCNN restorer (ablation)P2GAN with DnCNN · SIDD ValidationPSNR/SSIM: 0.96 dB/0.0085Improved
apply SC to UNet restorer (ablation)P2GAN with UNet · SIDD ValidationPSNR/SSIM: 1.58 dB/0.0373Improved

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