noise2noise 开源项目推荐（18 个）

yu4u /noise2noise

An unofficial and partial Keras implementation of "Noise2Noise: Learning Image Restoration without Clean Data"

madhavmk /Noise2Noise-audio_denoising_without_clean_training_data

Source code for the paper titled "Speech Denoising without Clean Training Data: a Noise2Noise Approach". Paper accepted at the INTERSPEECH 2021 conference. This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio denoising methods by showing that it is possible to train deep speech denoisi…

shivamsaboo17 /Deep-Restore-PyTorch

深度CNN，无需干净数据即可学习图像恢复！

ZhenyuTan /Noise2Noise-Cryo-EM-image-denoising

pytorch implementation of noise2noise for Cryo-EM image denoising

hanyoseob /pytorch-noise2noise

Noise2Noise: Learning Image Restoration without Clean Data

Kevinshao921 /Structure-Preserving-Noise2Noise

Official implementation of "Structure-Preserving Noise2Noise for Image Denoising with Zero-Shot Learning and L0 Gradient Minimization" (IEEE ICPECA 2026)

redrodion /setkafluo

Self-supervised (Noise2Noise) deep-learning denoising for X-ray fluorescence microscopy with multi-element detectors. TensorFlow. Anal. Chem. 2026.

MPI-Dortmund /sphire-janni

Just another noise 2 noise implementation (JANNI) with Keras

johnPertoft /noise2noise

Noise2Noise implementation

EliaFantini /Noise2Noise-Lite-two-ligther-versions-of-the-famous-AI-denoiser-for-small-images

Noise2Noise is an AI denoiser trained with noisy images only. We implemented a ligther version which trains faster on smaller pictures without losing performance and an even simpler one where every low-level component was implemented from scratch, including a reimplementation of autograd.

PINTO0309 /noise2noise

An unofficial and partial Keras implementation of "Noise2Noise: Learning Image Restoration without Clean Data" (AI can now fix your grainy photos by only looking at grainy photos. Noise2Noise)

the-pinbo /image-denoising

The standard approach to image reconstruction using deep learning is to use clean image priors for training purposes. In this project, we attempt to achieve denoising without using a clean image prior and yet, achieving a performance comparable to, or sometimes, even better than that obtained using the conventional approach.

evamn97 /emn-n2npytorch

Image reconstruction for AFM scans based on a pytorch implementation of Noise2Noise

DanielKhaykelson /dino-4dstem

DINO-SR self-supervised classifier for 4D-STEM diffraction: training, GUI, NL assistant (Ollama), NMF/ACOM/interpretation pipeline.

chiarapaglioni /MCRT

Self-supervised denoising for Monte Carlo Rendering

AlbianSalihu /Noise2Noise

Two Noise2Noise implementations for EPFL Deep Learning: an FFT-augmented U-Net (25.4 dB PSNR) and a full deep learning framework built from raw PyTorch tensors.

aamirmalik-dr /stem-denoising-restoration

Low-dose HAADF-STEM image restoration benchmark: classical denoisers vs CNN, scored by image fidelity and downstream atom detection

dyshang /noise2noise-revisited

Loss-controlled Noise2Noise study: the training pair distribution, not the loss function, carries the inductive bias. Code + per-image metric dumps.