The Surprising Effectiveness of Noise Pretraining for Implicit Neural Representations

• URL: http://arxiv.org/abs/2603.29034v1
• Date: Mon, 30 Mar 2026 22:01:00 GMT
• Title: The Surprising Effectiveness of Noise Pretraining for Implicit Neural Representations
• Abstract summary: We pretrain implicit neural representations (INRs) on diverse noise classes and measure their ability to fit unseen signals and encode priors for an inverse imaging task (denoising)<n>Our analyses on image and video data reveal a surprising finding: simply pretraining on unstructured noise improves signal fitting capacity compared to all other baselines.<n>This finding enables more efficient INR training in applications lacking sufficient prior domain-specific data.
• Score: 25.530854386619755
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The approximation and convergence properties of implicit neural representations (INRs) are known to be highly sensitive to parameter initialization strategies. While several data-driven initialization methods demonstrate significant improvements over standard random sampling, the reasons for their success -- specifically, whether they encode classical statistical signal priors or more complex features -- remain poorly understood. In this study, we explore this phenomenon through a series of experimental analyses leveraging noise pretraining. We pretrain INRs on diverse noise classes (e.g., Gaussian, Dead Leaves, Spectral) and measure their ability to both fit unseen signals and encode priors for an inverse imaging task (denoising). Our analyses on image and video data reveal a surprising finding: simply pretraining on unstructured noise (Uniform, Gaussian) dramatically improves signal fitting capacity compared to all other baselines. However, unstructured noise also yields poor deep image priors for denoising. In contrast, we also find that noise with the classic $1/|f^α|$ spectral structure of natural images achieves an excellent balance of signal fitting and inverse imaging capabilities, performing on par with the best data-driven initialization methods. This finding enables more efficient INR training in applications lacking sufficient prior domain-specific data. For more details, visit project page at https://kushalvyas.github.io/noisepretraining.html

Related papers

• Improving Accuracy and Efficiency of Implicit Neural Representations: Making SIREN a WINNER [0.0]
  We identify and address a fundamental limitation of sinusoidal representation networks (SIRENs)<n>In extreme cases, when the network's frequency support misaligns with the target spectrum, a'spectral bottleneck' is observed.<n>We propose WINNER - Weight Initialization with Noise for Neural Representations.
  arXiv  Detail & Related papers  (2025-09-16T11:41:13Z)
• Unrolled denoising networks provably learn optimal Bayesian inference [54.79172096306631]
  We prove the first rigorous learning guarantees for neural networks based on unrolling approximate message passing (AMP) For compressed sensing, we prove that when trained on data drawn from a product prior, the layers of the network converge to the same denoisers used in Bayes AMP.
  arXiv  Detail & Related papers  (2024-09-19T17:56:16Z)
• Beyond Image Prior: Embedding Noise Prior into Conditional Denoising Transformer [17.430622649002427]
  Existing learning-based denoising methods typically train models to generalize the image prior from large-scale datasets.<n>We propose a new perspective on the denoising challenge by highlighting the distinct separation between noise and image priors.<n>We introduce a Locally Noise Prior Estimation algorithm, which accurately estimates the noise prior directly from a single raw noisy image.
  arXiv  Detail & Related papers  (2024-07-12T08:43:11Z)
• Impact of Noisy Supervision in Foundation Model Learning [91.56591923244943]
  This paper is the first work to comprehensively understand and analyze the nature of noise in pre-training datasets.<n>We propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization.
  arXiv  Detail & Related papers  (2024-03-11T16:22:41Z)
• Unsupervised Denoising for Signal-Dependent and Row-Correlated Imaging Noise [54.0185721303932]
  We present the first fully unsupervised deep learning-based denoiser capable of handling imaging noise that is row-correlated as well as signal-dependent.<n>Our approach uses a Variational Autoencoder with a specially designed autoregressive decoder.<n>Our method does not require a pre-trained noise model and can be trained from scratch using unpaired noisy data.
  arXiv  Detail & Related papers  (2023-10-11T20:48:20Z)
• Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks [91.15120211190519]
  This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks. We propose a light-weight black-box tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise.
  arXiv  Detail & Related papers  (2023-09-29T06:18:15Z)
• CFNet: Conditional Filter Learning with Dynamic Noise Estimation for Real Image Denoising [37.29552796977652]
  This paper considers real noise approximated by heteroscedastic Gaussian/Poisson Gaussian distributions with in-camera signal processing pipelines. We propose a novel conditional filter in which the optimal kernels for different feature positions can be adaptively inferred by local features from the image and the noise map. Also, we bring the thought that alternatively performs noise estimation and non-blind denoising into CNN structure, which continuously updates noise prior to guide the iterative feature denoising.
  arXiv  Detail & Related papers  (2022-11-26T14:28:54Z)
• Poisson2Sparse: Self-Supervised Poisson Denoising From a Single Image [34.27748767631027]
  We present a novel self-supervised learning method for single-image denoising. We approximate traditional iterative optimization algorithms for image denoising with a recurrent neural network. Our method outperforms the state-of-the-art approaches in terms of PSNR and SSIM.
  arXiv  Detail & Related papers  (2022-06-04T00:08:58Z)
• The Optimal Noise in Noise-Contrastive Learning Is Not What You Think [80.07065346699005]
  We show that deviating from this assumption can actually lead to better statistical estimators. In particular, the optimal noise distribution is different from the data's and even from a different family.
  arXiv  Detail & Related papers  (2022-03-02T13:59:20Z)
• CycleISP: Real Image Restoration via Improved Data Synthesis [166.17296369600774]
  We present a framework that models camera imaging pipeline in forward and reverse directions. By training a new image denoising network on realistic synthetic data, we achieve the state-of-the-art performance on real camera benchmark datasets.
  arXiv  Detail & Related papers  (2020-03-17T15:20:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.