SLER-IR: Spherical Layer-wise Expert Routing for All-in-One Image Restoration
This work provides an incremental improvement for researchers and practitioners working on all-in-one image restoration tasks.
This paper addresses the challenge of unified all-in-one image restoration under diverse degradations, which often suffers from feature interference and insufficient expert specialization. The authors propose SLER-IR, a framework that dynamically activates specialized experts across network layers, achieving consistent improvements over state-of-the-art methods in PSNR and SSIM on three-task and five-task benchmarks.
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.