AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

MetaScope: Optics-Driven Neural Network for Ultra-Micro Metalens Endoscopy

Wuyang Li, Wentao Pan, Xiaoyuan Liu, Zhendong Luo, Chenxin Li, Hengyu Liu, Din Ping Tsai, Mu Ku Chen, Yixuan Yuan

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Retrieval and matching with generative features · 4 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 an auxiliary restoration branch guiding segmentation (ablation)MetaScope · Meta-CVC-ClinicmDICE: 0.8272 -> 0.8573Improved
add gradient-guided distillation from DINOv2 (instead of unguided distillation) (ablation)MetaScope · Meta-CVC-ClinicmDICE: 0.8750 -> 0.8927Improved
add Optics-informed Chromatic Correction (OCC) (ablation)MetaScope · Meta-CVC-ClinicPSNR: 32.8153 -> 34.0011Improved
use multi-expert Gaussian (MeG) in OCC (ablation)MetaScope OCC · Meta-CVC-ClinicPSNR: 32.8078 -> 34.0011Improved
add Optics-informed Intensity Adjustment (OIA) with optical prior (ablation)MetaScope · Meta-CVC-ClinicPSNR: 34.1341 -> 34.8483Improved
use simulated spatial plus channel optical priors instead of directly learned embedding (ablation)MetaScope OIA · Meta-EndoVis-17mIoU: 0.8700 -> 0.8802Improved
use 3 Gaussian experts instead of 1 (ablation)MetaScope OCC · Meta-EndoVis-17mIoU: 0.8682 -> 0.8802Improved
increase experts from 3 to 5 (ablation)MetaScope OCC · Meta-EndoVis-17mIoU: 0.8802 -> 0.8793No clear effect
raise restoration loss weight lambda from 0.1 to 1.0 (ablation)MetaScope · Meta-EndoVis-17mIoU: 0.8802 -> 0.8497Mixed
train one unified model on all five datasets versus DRMIMetaScope · Meta-CVC-Clinic restorationPSNR: 34.05 -> 36.47Improved
fine-tune on the new metalens (5 mm) after zero-shot transferMetaScope · Cross-metalens CVC-ClinicmIoU: 82.82 -> 86.37Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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