# Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks

arXiv: https://arxiv.org/abs/2003.07119 · HTML: https://mlsanity.com/paper/2003.07119/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2020.

## Built on by (most cited first, 21 of 21)

- [Towards Real-World Blind Face Restoration with Generative Facial Prior](https://mlsanity.com/paper/2101.04061/) (2021)
- [Exploiting the Signal-Leak Bias in Diffusion Models](https://mlsanity.com/paper/2309.15842/) (2023)
- [NTIRE 2021 Depth Guided Image Relighting Challenge](https://mlsanity.com/paper/2104.13365/) (2021)
- [Degradation-Guided Meta-Restoration Network for Blind Super-Resolution](https://mlsanity.com/paper/2207.00943/) (2022)
- [Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images](https://mlsanity.com/paper/2302.12491/) (2023)
- [PoGaIN: Poisson-Gaussian Image Noise Modeling from Paired Samples](https://mlsanity.com/paper/2210.04866/) (2022)
- [Stability and Generalizability in SDE Diffusion Models with Measure-Preserving Dynamics](https://mlsanity.com/paper/2406.13652/) (2024)
- [Deep Gaussian Denoiser Epistemic Uncertainty and Decoupled Dual-Attention Fusion](https://mlsanity.com/paper/2101.04631/) (2021)
- [Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks](https://mlsanity.com/paper/2106.00673/) (2021)
- [Learned, uncertainty-driven adaptive acquisition for photon-efficient scanning microscopy](https://mlsanity.com/paper/2310.16102/) (2023)
- [Learning degraded image classification with restoration data fidelity](https://mlsanity.com/paper/2101.09606/) (2021)
- [Universal Face Restoration With Memorized Modulation](https://mlsanity.com/paper/2110.01033/) (2021)
- [Image Denoising with Control over Deep Network Hallucination](https://mlsanity.com/paper/2201.00429/) (2022)
- [Kernelized Back-Projection Networks for Blind Super Resolution](https://mlsanity.com/paper/2302.08478/) (2023)
- [Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2509.22692/) (2025)
- [DRNet: All-in-One Image Restoration via Prior-Guided Dynamic Reparameterization](https://mlsanity.com/paper/2605.08627/) (2026)
- [Exploring ensembles and uncertainty minimization in denoising networks](https://mlsanity.com/paper/2101.09798/) (2021)
- [Controllable Confidence-Based Image Denoising](https://mlsanity.com/paper/2106.09311/) (2021)
- [DSR: Towards Drone Image Super-Resolution](https://mlsanity.com/paper/2208.12327/) (2022)
- [Towards Robust Drone Vision in the Wild](https://mlsanity.com/paper/2208.12655/) (2022)
- [Target Aware Poisson-Gaussian Noise Parameters Estimation from Noisy Images](https://mlsanity.com/paper/2210.12142/) (2022)

## Abstract (arXiv)

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.