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

TL;DR

LightBSR introduces a lightweight blind super-resolution model that enhances degradation representation discriminability through knowledge distillation, achieving high performance with minimal complexity.

Contribution

The paper proposes a novel lightweight BSR model, LightBSR, utilizing contrastive learning and knowledge transfer to improve implicit degradation representation discriminability.

Findings

LightBSR outperforms existing methods in blind super-resolution tasks.

The model achieves high accuracy with reduced parameters and computational cost.

Discriminability of degradation representations improves super-resolution quality.

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.