Ruofan Zhou and Majed El Helou's paper accepted to ECCV2020

© 2020 ECCV

© 2020 ECCV

The paper "Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks" accepted to ECCV2020. IVRL members Ruofan Zhou and Majed El Helou will present their work at the online European Conference on Computer Vision between 23-28 August 2020.

Super-resolution and denoising are ill-posed yet fundamental image restoration tasks. In blind settings, the degradation kernel or the noise level are unknown. This makes restoration even more challenging, notably for learning-based methods, as they tend to overfit to the degradation seen during training.
We present an analysis, in the frequency domain, of degradation-kernel overfitting in super-resolution and introduce a conditional learning perspective that extends to both super-resolution and denoising. Building on our formulation, we propose a stochastic frequency masking of images used in training to regularize the networks and address the overfitting problem. Our technique improves state-of-the-art methods on blind super-resolution with different synthetic kernels, real super-resolution, blind Gaussian denoising, and real-image denoising.


Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks
Authors : Majed El Helou, Ruofan Zhou, Sabine Süsstrunk