AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

From Enhancement to Understanding: Build a Generalized Bridge for Low-light Vision via Semantically Consistent Unsupervised Fine-tuning

Sen Wang, Shao Zeng, Tianjun Gu, Zhizhong Zhang, Ruixin Zhang, Shouhong Ding, Jingyun Zhang, Jun Wang, Xin Tan, Yuan Xie, Lizhuang Ma

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Zero-shot segmentation and detection · 5 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 illumination-aware image prompt to the baseline (ablation)CycleGAN-Turbo baseline · CODaN top-1 accuracyTop-1 accuracy (%): 57.24 -> 59.40Improved
add caption consistency on top of illumination-aware prompt (ablation)SCUF · LSRW image qualityPSNR (dB): 17.99 -> 16.98Hurt
add reflectance consistency with decoder-side placement (ablation)SCUF · LSRW image qualityPSNR (dB): 16.98 -> 18.48Improved
use cycle-attention adapter instead of IP-Adapter (ablation)SCUF · CODaN top-1 accuracyTop-1 accuracy (%): 59.84 -> 60.92Improved
add caption consistency to full model (ablation)SCUF · DARK FACE detectionmAP (%): 15.7 -> 16.9Improved
feed caption prompt directly to the text encoder instead of caption consistency (ablation)SCUF · CODaN top-1 accuracyTop-1 accuracy (%): 60.92 -> 60.08Hurt
add caption prompt to the plain baseline (ablation)CycleGAN-Turbo baseline · LSRW image qualityPSNR (dB): 14.42 -> 17.27Improved
enhance low-light images with SCUF before downstream modelsRefineNet on BDD100k-night · BDD100k-nightmIoU (%): 11.4 -> 20.1Improved
use SCUF instead of LightenDiffusion for image quality on LOLLOL (v2-real) · LOL (v2-real)PSNR (dB): 22.79 -> 21.32Hurt
improve image quality metrics of enhancerslow-light enhancement methods · downstream tasksdownstream accuracyNo clear effect
use SCUF instead of QuadPrior/LightDiff diffusion enhancers for efficiencypretrained diffusion enhancers · model complexityinference time (s): 2.443 -> 0.348Improved

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