UniH^3: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration
UniH3 unifies hierarchical homogeneity and heterogeneity modeling for all-in-one medical image restoration across modalities and degradation types.
UniH3 introduces a Hierarchical Homogeneity Memory module that distills shared anatomical priors from high-quality images, injected via a Homogeneity-Guided Attention mechanism. A Hierarchical Heterogeneity Balancer mitigates inter- and intra-task conflicts during multi-task optimization. It achieves state-of-the-art on MedIR-2D-500K and MedIR-3D-3D benchmarks for both all-in-one and single-task restoration, with code released on GitHub.
- H2M module retrieves homogeneity priors to guide restoration
- HGA mechanism injects retrieved priors into the pipeline
- H2B balancer addresses multi-task optimization conflicts
- SOTA on MedIR-2D-500K and MedIR-3D-3K benchmarks
- Code released at github.com/Yaziwel/UniH3
From the original article
1 min read at huggingface.co
All-in-One medical image restoration (MedIR) aims to address diverse tasks across modalities and degradation types using a single universal model. Existing methods typically prioritize modeling inter-task heterogeneity (e. g.
By Zhiwen Yang, Jiayin Li, Chengyu Liu · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.