# Towards Robust Image Denoising with Scale Equivariance

arXiv: https://arxiv.org/abs/2508.02967 · HTML: https://mlsanity.com/paper/2508.02967/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 5 Aug 2025.

## Builds on (most cited first, 19 of 19)

- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018)
- [Efficient and Explicit Modelling of Image Hierarchies for Image Restoration](https://mlsanity.com/paper/2303.00748/) (2023)
- [Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis](https://mlsanity.com/paper/2203.13278/) (2022)
- [Spatial-Adaptive Network for Single Image Denoising](https://mlsanity.com/paper/2001.10291/) (2020)
- [Zero-Shot Noise2Noise: Efficient Image Denoising without any Data](https://mlsanity.com/paper/2303.11253/) (2023)
- [Masked Image Training for Generalizable Deep Image Denoising](https://mlsanity.com/paper/2303.13132/) (2023)
- [Xformer: Hybrid X-Shaped Transformer for Image Denoising](https://mlsanity.com/paper/2303.06440/) (2023)
- [MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network](https://mlsanity.com/paper/2304.01598/) (2023)
- [Transfer CLIP for Generalizable Image Denoising](https://mlsanity.com/paper/2403.15132/) (2024)
- [Deep Variational Network Toward Blind Image Restoration](https://mlsanity.com/paper/2008.10796/) (2020)
- [Mixed Hierarchy Network for Image Restoration](https://mlsanity.com/paper/2302.09554/) (2023)
- [LAN: Learning to Adapt Noise for Image Denoising](https://mlsanity.com/paper/2412.10651/) (2024)
- [Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising](https://mlsanity.com/paper/2404.07846/) (2024)
- [Asymmetric Mask Scheme for Self-Supervised Real Image Denoising](https://mlsanity.com/paper/2407.06514/) (2024)
- [Rotation-Equivariant Self-Supervised Method in Image Denoising](https://mlsanity.com/paper/2505.19618/) (2025)
- [Learning to Translate Noise for Robust Image Denoising](https://mlsanity.com/paper/2412.04727/) (2024)

## Abstract (arXiv)

Despite notable advances in image denoising, existing models often struggle to generalize beyond in-distribution noise patterns, particularly when confronted with out-of-distribution (OOD) conditions characterized by spatially variant noise. This generalization gap remains a fundamental yet underexplored challenge. In this work, we investigate scale equivariance as a core inductive bias for improving OOD robustness. We argue that incorporating scale-equivariant structures enables models to better adapt from training on spatially uniform noise to inference on spatially non-uniform degradations. Building on this insight, we propose a robust blind denoising framework equipped with two key components: a Heterogeneous Normalization Module (HNM) and an Interactive Gating Module (IGM). HNM stabilizes feature distributions and dynamically corrects features under varying noise intensities, while IGM facilitates effective information modulation via gated interactions between signal and feature paths. Extensive evaluations demonstrate that our model consistently outperforms state-of-the-art methods on both synthetic and real-world benchmarks, especially under spatially heterogeneous noise. Code will be made publicly available.