AI Paper Atlas

Research map / Image generation / Image restoration

EndoIR: Degradation-Agnostic All-in-One Endoscopic Image Restoration via Noise-Aware Routing Diffusion

Tong Chen, Xinyu Ma, Long Bai, Wenyang Wang, Yue Sun, Luping Zhou

AAAI 2026 · Image generation › Image restoration · approach: Efficient restoration architectures · 3 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 Dual-Stream Encoder (ablation)EndoIR baseline · SegSTRONG-C averagePSNR: 30.39 -> 31.96Improved
add Task Adaptive Embedding (ablation)EndoIR baseline · SegSTRONG-C averagePSNR: 30.39 -> 31.40Improved
add Rectified Fusion Block (ablation)EndoIR baseline · SegSTRONG-C averagePSNR: 30.39 -> 31.56Improved
add RFB on top of TAE+DSE (ablation)EndoIR · SegSTRONG-C averagePSNR: 32.20 -> 32.36Improved
add RFB on top of TAE only (ablation)TAE · SegSTRONG-C averagePSNR: 31.40 -> 31.51Improved
use both spatial and frequency embeddings in Dual-Domain Prompter (ablation)Dual-Domain Prompter · SegSTRONG-C averagePSNR: 31.19 -> 32.36Improved
use FFT instead of wavelet transform in prompter (ablation)Dual-Domain Prompter · SegSTRONG-C averagePSNR: 31.96 -> 32.36Improved
reduce NARB channel selection ratio from 1 to 0.5 (ablation)Noise-Aware Routing Block · SegSTRONG-C averageSSIM: 87.05 -> 87.64 SSIM, 32.36 -> 32.23 PSNRMixed
select 0.75 of channels instead of 0.5 (ablation)Noise-Aware Routing Block · SegSTRONG-C averagePSNR: 32.23 -> 32.02Hurt
NARB with gamma 0.5 for efficiency (ablation)EndoIR · SegSTRONG-CParams (M) and FPS: 28.2 -> 21.3 M params, 8.14 -> 11.18 FPSImproved
EndoIR vs best baseline on CECEndoIR · CEC illumination correctionPSNR: 32.27 -> 32.65Improved
restore images with EndoIR before segmentationDeepLabV3+ segmentation · SegSTRONG-C downstreamDice: 95.47 -> 96.22Improved

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