LightBSR: Towards Lightweight Blind Super-Resolution via Discriminative Implicit Degradation Representation Learning

2025-06-27

AI Summary

Existing blind super-resolution (BSR) methods based on implicit degradation estimation (IDE-BSR) neglect the discriminability of implicit degradation representations (IDRs), leading to excessive model complexity, inflated parameter counts, and prohibitive computational overhead. To address this, we propose a discriminative implicit degradation representation learning framework. Our approach enhances IDR discriminability via degradation-prior-guided contrastive learning and achieves lightweight modeling through knowledge distillation and feature alignment. The resulting model accurately captures complex, real-world degradations while efficiently recovering high-frequency details—all with fewer than 0.5 million parameters and less than 1 Giga FLOPs. Extensive experiments demonstrate that our method outperforms both state-of-the-art lightweight and full-parameter BSR approaches across diverse blind SR benchmarks, achieving superior performance, computational efficiency, and strong generalization capability.

Technology Category

• Computer Vision: Representation Learning for Vision
• Machine Learning: Representation Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Implicit degradation estimation-based blind super-resolution (IDE-BSR) hinges on extracting the implicit degradation representation (IDR) of the LR image and adapting it to LR image features to guide HR detail restoration. Although IDE-BSR has shown potential in dealing with noise interference and complex degradations, existing methods ignore the importance of IDR discriminability for BSR and instead over-complicate the adaptation process to improve effect, resulting in a significant increase in the model's parameters and computations. In this paper, we focus on the discriminability optimization of IDR and propose a new powerful and lightweight BSR model termed LightBSR. Specifically, we employ a knowledge distillation-based learning framework. We first introduce a well-designed degradation-prior-constrained contrastive learning technique during teacher stage to make the model more focused on distinguishing different degradation types. Then we utilize a feature alignment technique to transfer the degradation-related knowledge acquired by the teacher to the student for practical inferencing. Extensive experiments demonstrate the effectiveness of IDR discriminability-driven BSR model design. The proposed LightBSR can achieve outstanding performance with minimal complexity across a range of blind SR tasks. Our code is accessible at: https://github.com/MJ-NCEPU/LightBSR.

Problem

• Enhancing discriminability of implicit degradation representation for BSR
• Reducing model complexity in blind super-resolution tasks
• Improving performance with lightweight design in SR models

Innovation

• Knowledge distillation-based learning framework
• Degradation-prior-constrained contrastive learning
• Feature alignment for knowledge transfer