DPC-Net: Dual-Prior Collaborative Network for All-in-One Image Restoration
All-in-One Image Restoration (AiOIR) aims to handle diverse degradations within a unified model. However, existing methods often overlook image semantics in degradation modeling and lack low-level visual priors during reconstruction, leading to structural distortions and semantic inconsistencies. To address these issues, we propose a novel Dual-Prior Collaborative Network (DPC-Net), which achieves high-quality restoration by jointly exploiting degradation-semantic coupled priors and low-level visual priors. Specifically, degraded images are fed into a Degradation-Aware Network (DAN) to extract
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%Tongyi-MAI/Z-Image-Turbo →
“Fuzzy title match (0.73): “DPC-Net: Dual-Prior Collaborative Network for All-in-One Ima” ≈ “Tongyi-MAI/Z-Image-Turbo””
- FuzzyOverlapping authors or contributors · 62%HKUDS/LightRAG →
“Shared author/contributor keys: jin”
- FuzzyOverlapping authors or contributors · 62%keras-team/keras →
“Shared author/contributor keys: jin”
- LinkedLinked via arxiv author · 85%Zhaokun He →
“DPC-Net: Dual-Prior Collaborative Network for All-in-One Image Restoration”
- LinkedLinked via arxiv author · 85%Kangbiao Shi →
“DPC-Net: Dual-Prior Collaborative Network for All-in-One Image Restoration”
- LinkedLinked via arxiv author · 85%Axi Niu →
“DPC-Net: Dual-Prior Collaborative Network for All-in-One Image Restoration”
- LinkedLinked via arxiv author · 85%Jian Jin →
“DPC-Net: Dual-Prior Collaborative Network for All-in-One Image Restoration”
- LinkedLinked via arxiv author · 85%Yupeng Wu →
“DPC-Net: Dual-Prior Collaborative Network for All-in-One Image Restoration”