AI Paper Atlas

Research map / Image generation / GANs

Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches

Xin Lin, Chao Ren, Xiao Liu, Jie Huang, Yinjie Lei

ICCV 2023 · Image generation › GANs · approach: GAN latent optimization and evaluation · 51 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 the NE module (noise extraction) to the generator input (ablation)GAN-based unsupervised denoiser · SIDD BenchmarkPSNR: 33.26 -> 33.45Improved
add BGM loss (ablation)GAN-based unsupervised denoiser · SIDD BenchmarkPSNR: 33.14 -> 33.26Improved
add self-synthesis constraint (ablation)V3 · SIDD BenchmarkPSNR: 33.45 -> 34.27Improved
use parallel two-branch design instead of single branch (ablation)SGabNet · SIDD BenchmarkPSNR: 34.27 -> 34.67Improved
add self-collaboration iterations (ablation)PGabNet (DeamNet) · SIDD BenchmarkPSNR: 34.67 -> 36.53Improved
add self-collaboration to DnCNN denoiser (ablation)PGabNet · SIDD BenchmarkPSNR: 30.56 -> 31.52Improved
add self-collaboration to UNet denoiser (ablation)PGabNet · SIDD BenchmarkPSNR: 34.63 -> 36.00Improved
add self-collaboration to DBSNL denoiser (ablation)PGabNet · SIDD BenchmarkPSNR: 34.29 -> 35.86Improved
later self-collaboration iterations (ablation)SCPGabNet · SIDD BenchmarkPSNR gain per iteration: first iteration >0.5dB; last 0.02dBNo clear effect
apply self-collaboration to DnCNN (ablation)PGabNet · DND BenchmarkSSIM: 0.7876 -> 0.7892No clear effect

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