Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution

• URL: http://arxiv.org/abs/2511.16024v1
• Date: Thu, 20 Nov 2025 04:11:44 GMT
• Title: Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution
• Authors: Xiao He, Zhijun Tu, Kun Cheng, Mingrui Zhu, Jie Hu, Nannan Wang, Xinbo Gao,
• Abstract summary: In real-world image super-resolution (Real-ISR), existing approaches mainly rely on fine-tuning pre-trained diffusion models.<n>We propose a Mixture-of-Ranks (MoR) architecture for single-step image super-resolution.<n>We introduce a fine-grained expert partitioning strategy that treats each rank in LoRA as an independent expert.
• Score: 76.66229730098759
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The demonstrated success of sparsely-gated Mixture-of-Experts (MoE) architectures, exemplified by models such as DeepSeek and Grok, has motivated researchers to investigate their adaptation to diverse domains. In real-world image super-resolution (Real-ISR), existing approaches mainly rely on fine-tuning pre-trained diffusion models through Low-Rank Adaptation (LoRA) module to reconstruct high-resolution (HR) images. However, these dense Real-ISR models are limited in their ability to adaptively capture the heterogeneous characteristics of complex real-world degraded samples or enable knowledge sharing between inputs under equivalent computational budgets. To address this, we investigate the integration of sparse MoE into Real-ISR and propose a Mixture-of-Ranks (MoR) architecture for single-step image super-resolution. We introduce a fine-grained expert partitioning strategy that treats each rank in LoRA as an independent expert. This design enables flexible knowledge recombination while isolating fixed-position ranks as shared experts to preserve common-sense features and minimize routing redundancy. Furthermore, we develop a degradation estimation module leveraging CLIP embeddings and predefined positive-negative text pairs to compute relative degradation scores, dynamically guiding expert activation. To better accommodate varying sample complexities, we incorporate zero-expert slots and propose a degradation-aware load-balancing loss, which dynamically adjusts the number of active experts based on degradation severity, ensuring optimal computational resource allocation. Comprehensive experiments validate our framework's effectiveness and state-of-the-art performance.

Related papers

• Degradation-Aware Metric Prompting for Hyperspectral Image Restoration [20.8230102672152]
  We propose a Degradation-Aware Metric Prompting (DAMP) framework to guide restoration of hyperspectral images.<n>Instead of relying on predefined degradation priors, we design spatial-spectral degradation metrics to continuously quantify degradations.<n>The framework enables adaptive, efficient, and robust restoration under diverse, mixed, or unseen degradations.
  arXiv  Detail & Related papers  (2025-12-23T11:05:36Z)
• Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding [54.05243949024302]
  Existing robust MLLMs rely on implicit training/adaptation that focuses solely on visual encoder generalization.<n>We propose Robust-R1, a novel framework that explicitly models visual degradations through structured reasoning chains.<n>Our approach integrates: (i) supervised fine-tuning for degradation-aware reasoning foundations, (ii) reward-driven alignment for accurately perceiving degradation parameters, and (iii) dynamic reasoning depth scaling adapted to degradation intensity.
  arXiv  Detail & Related papers  (2025-12-19T12:56:17Z)
• ClusIR: Towards Cluster-Guided All-in-One Image Restoration [72.16989784735796]
  ClusIR aims to recover high-quality images from diverse degradations within a unified framework.<n>ClusIR comprises two key components: a Probabilistic Cluster-Guided Routing Mechanism (PCGRM) and a Degradation-Aware Frequency Modulation Module (DAFMM)
  arXiv  Detail & Related papers  (2025-12-11T18:59:47Z)
• UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation [104.59740403500132]
  Multi-modal image segmentation faces real-world deployment challenges from incomplete/corrupted modalities degrading performance.<n>We propose a unified modality-relax segmentation network (UniMRSeg) through hierarchical self-supervised compensation (HSSC)<n>Our approach hierarchically bridges representation gaps between complete and incomplete modalities across input, feature and output levels.
  arXiv  Detail & Related papers  (2025-09-19T17:29:25Z)
• GENRE-CMR: Generalizable Deep Learning for Diverse Multi-Domain Cardiac MRI Reconstruction [0.8749675983608171]
  We propose GENRE-CMR, a generative adversarial network (GAN)-based architecture to enhance reconstruction fidelity and generalization.<n>Experiments confirm that GENRE-CMR surpasses state-of-the-art methods on training and unseen data, achieving 0.9552 SSIM and 38.90 dB PSNR on unseen distributions.<n>Our framework presents a unified and robust solution for high-quality CMR reconstruction, paving the way for clinically adaptable deployment across heterogeneous acquisition protocols.
  arXiv  Detail & Related papers  (2025-08-28T09:43:59Z)
• FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE [21.860699562235776]
  FLAME is a novel federated learning framework based on the Sparse Mixture-of-Experts (SMoE) architecture.<n>It retains full (uncompressed) global LoRA matrices and achieves client-side adaptability by varying the number of activated experts per client.<n>It tackles these challenges through a lightweight rescaling mechanism and an activation-aware aggregation scheme.
  arXiv  Detail & Related papers  (2025-06-19T21:02:19Z)
• From Controlled Scenarios to Real-World: Cross-Domain Degradation Pattern Matching for All-in-One Image Restoration [2.997052569698842]
  All-in-One Image Restoration (AiOIR) aims to achieve image restoration caused by multiple degradation patterns via a single model with unified parameters.<n>UDAIR framework is proposed to effectively achieve AiOIR by leveraging the learned knowledge from source domain to target domain.<n> Experimental results on 10 open-source datasets demonstrate that UDAIR achieves new state-of-the-art performance for the AiOIR task.
  arXiv  Detail & Related papers  (2025-05-28T12:22:00Z)
• InvFussion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems [76.39776789410088]
  This work introduces a framework that combines the strong performance of supervised approaches and the flexibility of zero-shot methods.<n>A novel architectural design seamlessly integrates the degradation operator directly into the denoiser.<n> Experimental results on the FFHQ and ImageNet datasets demonstrate state-of-the-art posterior-sampling performance.
  arXiv  Detail & Related papers  (2025-04-02T12:40:57Z)
• LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration [62.3751291442432]
  We propose LoRA-IR, a flexible framework that dynamically leverages compact low-rank experts to facilitate efficient all-in-one image restoration. LoRA-IR consists of two training stages: degradation-guided pre-training and parameter-efficient fine-tuning. Experiments demonstrate that LoRA-IR achieves SOTA performance across 14 IR tasks and 29 benchmarks, while maintaining computational efficiency.
  arXiv  Detail & Related papers  (2024-10-20T13:00:24Z)
• Multi-Agent Reinforcement Learning for Adaptive Mesh Refinement [17.72127385405445]
  We present a novel formulation of adaptive mesh refinement (AMR) as a fully-cooperative Markov game. We design a novel deep multi-agent reinforcement learning algorithm called Value Decomposition Graph Network (VDGN) We show that VDGN policies significantly outperform error threshold-based policies in global error and cost metrics.
  arXiv  Detail & Related papers  (2022-11-02T00:41:32Z)
• Reinforcement Learning for Adaptive Mesh Refinement [63.7867809197671]
  We propose a novel formulation of AMR as a Markov decision process and apply deep reinforcement learning to train refinement policies directly from simulation. The model sizes of these policy architectures are independent of the mesh size and hence scale to arbitrarily large and complex simulations.
  arXiv  Detail & Related papers  (2021-03-01T22:55:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.