AI Paper Atlas

Research map / Detection and segmentation / CNN features

NUN: Nested Unfolding Network for Real-World Concealed Object Segmentation

Chunming He, Rihan Zhang, Longxiang Tang, Dingming Zhang, Bojian Zhang, Fengyang Xiao, Jingjia Feng, Sina Farsiu

ECCV 2026 · Detection and segmentation › CNN features · approach: Joint detection and instance segmentation

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 DeRUN restoration unfolding network (ablation)SODUN · COD10K combined degradationF_beta: 0.362 -> 0.406Improved
add bi-directional unfolding interaction (BUI) (ablation)SODUN + DeRUN · COD10K combined degradationF_beta: 0.406 -> 0.448Improved
add SODUN background estimation (ablation)SODUN- · COD10K combined degradationF_beta: 0.328 -> 0.362Improved
use DA-CLIP explicit degradation prior instead of implicit prior (ablation)DeRUN · COD10K combined degradationF_beta: 0.422 -> 0.448Improved
add segmentation cues X2 in DeRUN (ablation)DeRUN · COD10K combined degradationF_beta: 0.430 -> 0.448Improved
add IQA-based selection of best restoration (ablation)BUI · COD10K combined degradationF_beta: 0.421 -> 0.448Improved
add cross-stage consistency loss (ablation)BUI · COD10K combined degradationF_beta: 0.428 -> 0.448Improved
use simple 3-layer network instead of complex transformer for background estimation (ablation)SODUN · COD10K combined degradationF_beta: 0.447 -> 0.448No clear effect
NUN vs RUN under combined degradationNUN · COD10K combined degradation (PVT V2)F_beta: 0.429 -> 0.732Improved
NUN vs RUN on clean COD10KNUN · COD10K clean (ResNet50)F_beta: 0.747 -> 0.759Improved
NUN adds restoration/segmentation nesting at compute costNUN · COD efficiency (ResNet50)FPS: 22.75 -> 20.10Hurt
integrate NUN framework into existing models instead of pre-restoration or bi-level optimizationFEDER · COD10K combined degradationF_beta: 0.322 -> 0.416Improved

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