AI Paper Atlas

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

Restoration Adaptation for Semantic Segmentation on Low Quality Images

Kai Guan, Rongyuan Wu, Shuai Li, Wentao Zhu, Wenjun Zeng, Lei Zhang

IJCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 1 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 restoration adaptation with SCR before segmentation training (ablation)RASS · ADE20K (simulated LQ)mIoU: 44.56 -> 47.42Improved
use SCR instead of OSEDiff+ for restoration adaptation (ablation)RASS · ADE20K (simulated LQ)mIoU: 47.05 -> 47.42Improved
use SCR instead of OSEDiff as restoration before segmentation (R2S) (ablation)RASS · ADE20K (simulated LQ)mIoU: 46.05 -> 46.81Improved
add VAE encoder features to UNet features (ablation)RASS · ADE20K (simulated LQ)mIoU: 46.85 -> 47.42Improved
add VAE decoder features to UNet features (ablation)RASS · ADE20K (simulated LQ)mIoU: 46.85 -> 47.25Improved
add both VAE encoder and decoder features (ablation)RASS · ADE20K (simulated LQ)mIoU: 47.42 -> 47.60Improved
add additional descriptions (AD) in SCR training (ablation)SCR · DrealSRMANIQA: 0.6338 -> 0.6394Improved
enable additional descriptions at inference (ablation)SCR · DrealSRMUSIQ: 67.15 -> 67.16No clear effect
reduce SCR training data from all 84,991 to 1,000 LSDIR images (ablation)SCR · DrealSRPSNR: 28.54 -> 28.45No clear effect
use 475 curated LSDIR images instead of all images (ablation)SCR · DrealSRMUSIQ: 64.51 -> 69.12; PSNR 28.54 -> 27.43Mixed
add 518 enhanced ADE20K images to the 475 LSDIR images (ablation)SCR · DrealSRPSNR: 27.43 -> 28.14Improved
use fine-tuning on LQ data instead of direct testing for baselines on RealLQFeedFormer and SeaFormer · RealLQmIoU: 20.87 -> 19.19; 15.52 -> 14.97Hurt

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