SLER-IR: Spherical Layer-wise Expert Routing for All-in-One Image Restoration

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shurui, Peng, Lin, Xin, Luo, Shi, Ou, Jincen, Zhang, Dizhe, Qi, Lu, Nguyen, Truong, Ren, Chao
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908869990547456
author Shurui, Peng
Lin, Xin
Luo, Shi
Ou, Jincen
Zhang, Dizhe
Qi, Lu
Nguyen, Truong
Ren, Chao
author_facet Shurui, Peng
Lin, Xin
Luo, Shi
Ou, Jincen
Zhang, Dizhe
Qi, Lu
Nguyen, Truong
Ren, Chao
contents Image restoration under diverse degradations remains challenging for unified all-in-one frameworks due to feature interference and insufficient expert specialization. We propose SLER-IR, a spherical layer-wise expert routing framework that dynamically activates specialized experts across network layers. To ensure reliable routing, we introduce a Spherical Uniform Degradation Embedding with contrastive learning, which maps degradation representations onto a hypersphere to eliminate geometry bias in linear embedding spaces. In addition, a Global-Local Granularity Fusion (GLGF) module integrates global semantics and local degradation cues to address spatially non-uniform degradations and the train-test granularity gap. Experiments on three-task and five-task benchmarks demonstrate that SLER-IR achieves consistent improvements over state-of-the-art methods in both PSNR and SSIM. Code and models will be publicly released.
format Preprint
id arxiv_https___arxiv_org_abs_2603_05940
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SLER-IR: Spherical Layer-wise Expert Routing for All-in-One Image Restoration
Shurui, Peng
Lin, Xin
Luo, Shi
Ou, Jincen
Zhang, Dizhe
Qi, Lu
Nguyen, Truong
Ren, Chao
Computer Vision and Pattern Recognition
Image restoration under diverse degradations remains challenging for unified all-in-one frameworks due to feature interference and insufficient expert specialization. We propose SLER-IR, a spherical layer-wise expert routing framework that dynamically activates specialized experts across network layers. To ensure reliable routing, we introduce a Spherical Uniform Degradation Embedding with contrastive learning, which maps degradation representations onto a hypersphere to eliminate geometry bias in linear embedding spaces. In addition, a Global-Local Granularity Fusion (GLGF) module integrates global semantics and local degradation cues to address spatially non-uniform degradations and the train-test granularity gap. Experiments on three-task and five-task benchmarks demonstrate that SLER-IR achieves consistent improvements over state-of-the-art methods in both PSNR and SSIM. Code and models will be publicly released.
title SLER-IR: Spherical Layer-wise Expert Routing for All-in-One Image Restoration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.05940