AI Paper Atlas

Research map / Image generation / Image restoration

Learning to See in the Extremely Dark

Hai Jiang, Binhao Guan, Zhen Liu, Xiaohong Liu, Jian Yu, Zheng Liu, Songchen Han, Shuaicheng Liu

ICCV 2025 · Image generation › Image restoration · approach: Low-light image enhancement · 15 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
use multi-stage training instead of single-stage joint training (ablation)SIED diffusion framework · SIED Canon 0.01-0.1 luxPSNR: 22.96 -> 24.85Improved
use multi-stage training instead of single-stage joint training (ablation)SIED diffusion framework · SIED Canon 0.01-0.1 luxLPIPS: 0.431 -> 0.360Improved
add Adaptive Illumination Correction Module (ablation)SIED diffusion framework · SIED Canon 0.01-0.1 luxPSNR: 23.23 -> 24.85Improved
add AICM (ablation)SIED diffusion framework · SIED Canon 0.01-0.1 luxSSIM: 0.839 -> 0.849Improved
add AICM (ablation)SIED diffusion framework · SIED Canon 0.01-0.1 luxLPIPS: 0.378 -> 0.360Improved
use AICM instead of fixed amplification factor 100 (ablation)SIED diffusion framework · SIED Canon 0.01-0.1 luxPSNR: 23.74 -> 24.85Improved
use AICM instead of fixed amplification factor 200 (ablation)SIED diffusion framework · SIED Canon 0.01-0.1 luxPSNR: 23.48 -> 24.85Improved
use AICM instead of fixed amplification factor 300 (ablation)SIED diffusion framework · SIED Canon 0.01-0.1 luxPSNR: 23.18 -> 24.85Improved
add color consistency loss (ablation)SIED diffusion framework · SIED Canon 0.01-0.1 luxPSNR: 24.53 -> 24.85Improved
add color consistency loss (ablation)SIED diffusion framework · SIED Canon 0.01-0.1 luxSSIM: 0.836 -> 0.849Improved
add color consistency loss (ablation)SIED diffusion framework · SIED Canon 0.01-0.1 luxLPIPS: 0.389 -> 0.360Improved
multi-stage framework vs single-stage competitorsMulti-stage methods · SIEDPSNR/SSIM/LPIPSImproved

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