Metric Learning based Interactive Modulation for Real-World Super-Resolution

by   Chong Mou, et al.

Interactive image restoration aims to restore images by adjusting several controlling coefficients, which determine the restoration strength. Existing methods are restricted in learning the controllable functions under the supervision of known degradation types and levels. They usually suffer from a severe performance drop when the real degradation is different from their assumptions. Such a limitation is due to the complexity of real-world degradations, which can not provide explicit supervision to the interactive modulation during training. However, how to realize the interactive modulation in real-world super-resolution has not yet been studied. In this work, we present a Metric Learning based Interactive Modulation for Real-World Super-Resolution (MM-RealSR). Specifically, we propose an unsupervised degradation estimation strategy to estimate the degradation level in real-world scenarios. Instead of using known degradation levels as explicit supervision to the interactive mechanism, we propose a metric learning strategy to map the unquantifiable degradation levels in real-world scenarios to a metric space, which is trained in an unsupervised manner. Moreover, we introduce an anchor point strategy in the metric learning process to normalize the distribution of metric space. Extensive experiments demonstrate that the proposed MM-RealSR achieves excellent modulation and restoration performance in real-world super-resolution. Codes are available at


page 2

page 5

page 9

page 10

page 11

page 14

page 16

page 17


Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution

Efficient and effective real-world image super-resolution (Real-ISR) is ...

Multi-Dimension Modulation for Image Restoration with Dynamic Controllable Residual Learning

Based on the great success of deterministic learning, to interactively c...

Toward Interactive Modulation for Photo-Realistic Image Restoration

Modulating image restoration level aims to generate a restored image by ...

Bayesian Image Super-Resolution with Deep Modeling of Image Statistics

Modeling statistics of image priors is useful for image super-resolution...

Panini-Net: GAN Prior Based Degradation-Aware Feature Interpolation for Face Restoration

Emerging high-quality face restoration (FR) methods often utilize pre-tr...

Sparsity-Aware Optimal Transport for Unsupervised Restoration Learning

Recent studies show that, without any prior model, the unsupervised rest...

Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off

Super-resolution (SR) techniques designed for real-world applications co...

Please sign up or login with your details

Forgot password? Click here to reset