Skip to content
AI Atlas
PaperActive

UniH$^3$: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration

arxiv.org/abs/2609.11156

Explore graph

Updated 43 min ago · first seen 11 Sept 2026

paper_01M294H1TZ888GG2SDGCAZ7AKE

Published
11 Sept 2026
T1 · 52 min ago
arXiv
2609.11156
T1 · 52 min ago
Category
cs.CV
T1 · 52 min ago

Abstract

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., distinct data distributions and degradation types). However, they largely neglect the inherent homogeneity present in medical images, such as widely shared anatomical structures within and across modalities, which can be leveraged to ease model training and improve generalization. To this end, we propose UniH3, a novel framework that Unifies Hierarchical Homogeneity and Heterogeneity for all-in-one medical image restoration. Specifically, to comprehensively exploit homogeneity, we introduce a Hierarchical Homogeneity Memory (H2M) module that progressively distills intra- and inter-task homogeneity priors from high-quality images during training, and adaptively retrieves the most relevant priors tailored to the input for guided restoration. These retrieved priors are then injected into the restoration pipeline via an efficient Homogeneity-Guided Attention (HGA) mechanism. Furthermore, to comprehensively address heterogeneity, we design a Hierarchical Heterogeneity Balancer (H2B) that mitigates both inter- and intra-task conflicts during optimization, facilitating balanced and effective multi-task learning. Extensive experiments on two large-scale benchmarks, MedIR-2D-500K and MedIR-3D-3K, demonstrate that UniH3 achieves state-of-the-art performance on both all-in-one and single-task medical image restoration. We hope this work establishes a strong benchmark and advances the development of general-purpose medical image restoration models. Code is available at https://github.com/Yaziwel/UniH3.

Authors 6

Zhiwen Yang, Jiayin Li, Chengyu Liu, Hui Zhang, Bingzheng Wei, Yan Xu

Specification

Official page
arxiv.org/abs/2609.11156

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Arxiv announce type
new

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

arXiv id
2609.11156

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Categories
cs.CV

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Github repo
Yaziwel/UniH3

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 45 min agomedium

Hf paper url
https://huggingface.co/papers/2609.11156

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 45 min agomedium

Github stars
5

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 43 min agomedium

Hf comments
1

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 43 min agomedium

Upvotes
2

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 43 min agomedium

PDF
arxiv.org/pdf/2609.11156

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Primary category
cs.CV

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

14

Source tiers

T1T29 / 5

Freshest observation

43 min ago

Conflicts

2 flagged