mlsanityData to 7 Oct 2026

Zero-shot Blind Image Denoising via Implicit Neural Representations

arXiv 2204.02405 ↗First posted 5 Apr 2022eess.IV cs.AI cs.CVcited by 12

Not on the map. Why?

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.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 5 Apr 2022.

Builds on

16 of 30 references.

References · 16

  1. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  2. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  4. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  5. 2017Deep Image Priorcited by 1,097
  6. 2021Multi-Stage Progressive Image Restorationcited by 813
  7. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  8. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
  9. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  10. 2021HINet: Half Instance Normalization Network for Image Restorationcited by 236
  11. 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
  12. 2019Variational Denoising Network: Toward Blind Noise Modeling and Removalcited by 117
4 more
  1. 2018Real-world Noisy Image Denoising: A New Benchmarkcited by 74
  2. 2018A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Imagescited by 70
  3. 2017When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approachcited by 42
  4. 2019The Spectral Bias of the Deep Image Priorcited by 20

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 2; 2024: 4; 2025: 2.

12 papers.

  1. 2023Zero-Shot Noise2Noise: Efficient Image Denoising without any Datacited by 59
  2. 2024Bidirectional Multi-Scale Implicit Neural Representations for Image Derainingcited by 54
  3. 2022Low-Rank Tensor Function Representation for Multi-Dimensional Data Recoverycited by 45
  4. 2023Continuous-Time Functional Diffusion Processescited by 39
  5. 2024Revisiting Nonlocal Self-Similarity from Continuous Representationcited by 14
  6. 2024Towards Croppable Implicit Neural Representationscited by 5
  7. 2022PIP: Positional-encoding Image Priorcited by 3
  8. 2024INRetouch: Context Aware Implicit Neural Representation for Photography Retouchingcited by 3
  9. 2022Scale-Agnostic Super-Resolution in MRI using Feature-Based Coordinate Networkscited by 2
  10. 2025Data Denoising and Derivative Estimation for Data-Driven Modeling of Nonlinear Dynamical Systemscited by 1
  11. 2022Domino Denoise: An Accurate Blind Zero-Shot Denoiser using Domino Tilingscited by 0
  12. 2025SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppressioncited by 0