# Implicit Neural Speckle Denoising

arXiv: https://arxiv.org/abs/2608.06574 · HTML: https://mlsanity.com/paper/2608.06574/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 49 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [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)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Plug-and-Play Image Restoration with Deep Denoiser Prior](https://mlsanity.com/paper/2008.13751/) (2020)
- [WIRE: Wavelet Implicit Neural Representations](https://mlsanity.com/paper/2301.05187/) (2023)
- [FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation](https://mlsanity.com/paper/1907.01361/) (2019)
- [Time-Dependent Deep Image Prior for Dynamic MRI](https://mlsanity.com/paper/1910.01684/) (2019)
- [Recovery of Continuous 3D Refractive Index Maps from Discrete Intensity-Only Measurements using Neural Fields](https://mlsanity.com/paper/2112.00002/) (2021)
- [Scalable Log Determinants for Gaussian Process Kernel Learning](https://mlsanity.com/paper/1711.03481/) (2017)
- [Speckle2Void: Deep Self-Supervised SAR Despeckling with Blind-Spot Convolutional Neural Networks](https://mlsanity.com/paper/2007.02075/) (2020)
- [As if by magic: self-supervised training of deep despeckling networks with MERLIN](https://mlsanity.com/paper/2110.13148/) (2021)
- [Deep Video Prior for Video Consistency and Propagation](https://mlsanity.com/paper/2201.11632/) (2022)
- [Phase-error estimation and image reconstruction from digital-holography data using a Bayesian framework](https://mlsanity.com/paper/1708.01142/) (2017)
- [Multilook Coherent Imaging: Theoretical Guarantees and Algorithms](https://mlsanity.com/paper/2505.23594/) (2025)
- [CLAMP: Majorized Plug-and-Play for Coherent 3D LIDAR Imaging](https://mlsanity.com/paper/2406.13651/) (2024)
- [Maximum Likelihood Reconstruction for Multi-Look Digital Holography with Markov-Modeled Speckle Correlation](https://mlsanity.com/paper/2604.20154/) (2026)

## Abstract (arXiv)

Speckle fundamentally limits coherent imaging by introducing multiplicative, spatially correlated noise that obscures scene structure. Removing speckle noise from dynamic scenes--that do not benefit from conventional speckle averaging--is particularly challenging. We introduce a training-free framework that combines a spatiotemporal implicit neural representation with an aperture-aware maximum-likelihood formulation to recover dynamic, speckle-free imagery directly from noisy observations. The coherent likelihood explicitly models the aperture-dependent spatial covariance of speckle, enabling adaptation to arbitrary pupil geometries without retraining. A matrix-free implementation based on FFT-accelerated operators, stochastic approximations, and conjugate gradients makes optimization practical for realistic image sizes. Meanwhile, a blind holdout criterion provides automatic early stopping without clean reference data. Simulated and laboratory results demonstrate improved spatial fidelity, temporal consistency, and robustness to varying speckle statistics relative to classical, unsupervised, and supervised baselines.