提出球面分层专家路由，提升图像修复统一框架的泛化能力。
SLER-IR: Spherical Layer-wise Expert Routing for All-in-One Image Restoration
- 基于球面嵌入动态激活各层专用专家，减少特征干扰。
- 在三任务与五任务基准上均超越当前最优方法，PSNR与SSIM双提升。
- 适合需要处理多种退化类型的图像修复场景。
多样退化下的图像修复对统一的全功能框架仍具挑战，主要源于特征干扰和专家专属性不足。本文提出SLER-IR，一种球面分层专家路由框架，可在网络各层动态激活专用专家。为确保路由可靠性，引入带有对比学习的球面均匀退化嵌入（Spherical Uniform Degradation Embedding），将退化表征映射至超球面，消除线性嵌入空间中的几何偏差。此外，全局-局部粒度融合（GLGF）模块整合全局语义与局部退化线索，解决空间非均匀退化及训练-测试粒度差异问题。在三任务与五任务基准上的实验表明，SLER-IR在PSNR与SSIM指标上均持续优于当前最优方法。代码与模型将公开发布。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。