# Training Deep Learning Based Denoisers without Ground Truth Data

arXiv: https://arxiv.org/abs/1803.01314 · HTML: https://mlsanity.com/paper/1803.01314/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2018.

## Built on by (most cited first, 30 of 43)

- [Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images](https://mlsanity.com/paper/2101.02824/) (2021)
- [Zero-Shot Noise2Noise: Efficient Image Denoising without any Data](https://mlsanity.com/paper/2303.11253/) (2023)
- [Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurements](https://mlsanity.com/paper/2111.12855/) (2021)
- [Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data](https://mlsanity.com/paper/2404.10177/) (2024)
- [Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data](https://mlsanity.com/paper/2305.01166/) (2023)
- [GSURE-Based Diffusion Model Training with Corrupted Data](https://mlsanity.com/paper/2305.13128/) (2023)
- [Rethinking Deep Image Prior for Denoising](https://mlsanity.com/paper/2108.12841/) (2021)
- [Optimal Transport for Unsupervised Denoising Learning](https://mlsanity.com/paper/2108.02574/) (2021)
- [FBI-Denoiser: Fast Blind Image Denoiser for Poisson-Gaussian Noise](https://mlsanity.com/paper/2105.10967/) (2021)
- [Self-Supervised Image Restoration with Blurry and Noisy Pairs](https://mlsanity.com/paper/2211.07317/) (2022)
- [Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling](https://mlsanity.com/paper/2307.03992/) (2023)
- [Unleashing the Power of Self-Supervised Image Denoising: A Comprehensive Review](https://mlsanity.com/paper/2308.00247/) (2023)
- [Adaptive Denoising via GainTuning](https://mlsanity.com/paper/2107.12815/) (2021)
- [The Devil is in the Upsampling: Architectural Decisions Made Simpler for Denoising with Deep Image Prior](https://mlsanity.com/paper/2304.11409/) (2023)
- [Deformation-Compensated Learning for Image Reconstruction without Ground Truth](https://mlsanity.com/paper/2107.05533/) (2021)
- [Deep Internal Learning: Deep Learning from a Single Input](https://mlsanity.com/paper/2312.07425/) (2023)
- [Score-based Self-supervised MRI Denoising](https://mlsanity.com/paper/2505.05631/) (2025)
- [Image Restoration by Deep Projected GSURE](https://mlsanity.com/paper/2102.02485/) (2021)
- [Self-Supervised Scalable Deep Compressed Sensing](https://mlsanity.com/paper/2308.13777/) (2023)
- [A Comparison of Image Denoising Methods](https://mlsanity.com/paper/2304.08990/) (2023)
- [Patch-Craft Self-Supervised Training for Correlated Image Denoising](https://mlsanity.com/paper/2211.09919/) (2022)
- [Robust multi-coil MRI reconstruction via self-supervised denoising](https://mlsanity.com/paper/2411.12919/) (2024)
- [Evaluating Unsupervised Denoising Requires Unsupervised Metrics](https://mlsanity.com/paper/2210.05553/) (2022)
- [Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurements](https://mlsanity.com/paper/2510.11964/) (2025)
- [Deep Variation Prior: Joint Image Denoising and Noise Variance Estimation without Clean Data](https://mlsanity.com/paper/2209.09214/) (2022)
- [DeCompress: Denoising via Neural Compression](https://mlsanity.com/paper/2503.22015/) (2025)
- [A Field of Experts Prior for Adapting Neural Networks at Test Time](https://mlsanity.com/paper/2202.05271/) (2022)
- [Self-supervised regression learning using domain knowledge: Applications to improving self-supervised denoising in imaging](https://mlsanity.com/paper/2205.04821/) (2022)
- [On normalization-equivariance properties of supervised and unsupervised denoising methods: a survey](https://mlsanity.com/paper/2402.15352/) (2024)
- [Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework](https://mlsanity.com/paper/2506.12693/) (2025)

## Abstract (arXiv)

Recently developed deep-learning-based denoisers often outperform state-of-the-art conventional denoisers such as the BM3D. They are typically trained to minimize the mean squared error (MSE) between the output image of a deep neural network (DNN) and a ground truth image. Thus, it is important for deep-learning-based denoisers to use high quality noiseless ground truth data for high performance. However, it is often challenging or even infeasible to obtain noiseless images in some applications. Here, we propose a method based on Stein's unbiased risk estimator (SURE) for training DNN denoisers based only on the use of noisy images in the training data with Gaussian noise. We demonstrate that our SURE-based method, without the use of ground truth data, is able to train DNN denoisers to yield performances close to those networks trained with ground truth for both grayscale and color images. We also propose a SURE-based refining method with a noisy test image for further performance improvement. Our quick refining method outperformed conventional BM3D, deep image prior, and often the networks trained with ground truth. Potential extension of our SURE-based methods to Poisson noise model was also investigated.