# Zero-shot Blind Image Denoising via Implicit Neural Representations

arXiv: https://arxiv.org/abs/2204.02405 · HTML: https://mlsanity.com/paper/2204.02405/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 5 Apr 2022.

## Builds on (most cited first, 16 of 16)

- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [HINet: Half Instance Normalization Network for Image Restoration](https://mlsanity.com/paper/2105.06086/) (2021)
- [High-Quality Self-Supervised Deep Image Denoising](https://mlsanity.com/paper/1901.10277/) (2019)
- [Variational Denoising Network: Toward Blind Noise Modeling and Removal](https://mlsanity.com/paper/1908.11314/) (2019)
- [Real-world Noisy Image Denoising: A New Benchmark](https://mlsanity.com/paper/1804.02603/) (2018)
- [A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Images](https://mlsanity.com/paper/1812.10366/) (2018)
- [When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach](https://mlsanity.com/paper/1706.04284/) (2017)
- [The Spectral Bias of the Deep Image Prior](https://mlsanity.com/paper/1912.08905/) (2019)

## Built on by (most cited first, 12 of 12)

- [Zero-Shot Noise2Noise: Efficient Image Denoising without any Data](https://mlsanity.com/paper/2303.11253/) (2023)
- [Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining](https://mlsanity.com/paper/2404.01547/) (2024)
- [Low-Rank Tensor Function Representation for Multi-Dimensional Data Recovery](https://mlsanity.com/paper/2212.00262/) (2022)
- [Continuous-Time Functional Diffusion Processes](https://mlsanity.com/paper/2303.00800/) (2023)
- [Revisiting Nonlocal Self-Similarity from Continuous Representation](https://mlsanity.com/paper/2401.00708/) (2024)
- [Towards Croppable Implicit Neural Representations](https://mlsanity.com/paper/2409.19472/) (2024)
- [PIP: Positional-encoding Image Prior](https://mlsanity.com/paper/2211.14298/) (2022)
- [INRetouch: Context Aware Implicit Neural Representation for Photography Retouching](https://mlsanity.com/paper/2412.03848/) (2024)
- [Scale-Agnostic Super-Resolution in MRI using Feature-Based Coordinate Networks](https://mlsanity.com/paper/2210.08676/) (2022)
- [Data Denoising and Derivative Estimation for Data-Driven Modeling of Nonlinear Dynamical Systems](https://mlsanity.com/paper/2509.14219/) (2025)
- [Domino Denoise: An Accurate Blind Zero-Shot Denoiser using Domino Tilings](https://mlsanity.com/paper/2212.02439/) (2022)
- [SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppression](https://mlsanity.com/paper/2509.07373/) (2025)

## Abstract (arXiv)

Recent denoising algorithms based on the "blind-spot" strategy show impressive blind image denoising performances, without utilizing any external dataset. While the methods excel in recovering highly contaminated images, we observe that such algorithms are often less effective under a low-noise or real noise regime. To address this gap, we propose an alternative denoising strategy that leverages the architectural inductive bias of implicit neural representations (INRs), based on our two findings: (1) INR tends to fit the low-frequency clean image signal faster than the high-frequency noise, and (2) INR layers that are closer to the output play more critical roles in fitting higher-frequency parts. Building on these observations, we propose a denoising algorithm that maximizes the innate denoising capability of INRs by penalizing the growth of deeper layer weights. We show that our method outperforms existing zero-shot denoising methods under an extensive set of low-noise or real-noise scenarios.