# Self2Self+: Single-Image Denoising with Self-Supervised Learning and Image Quality Assessment Loss

arXiv: https://arxiv.org/abs/2307.10695 · HTML: https://mlsanity.com/paper/2307.10695/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 20 Jul 2023.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment](https://mlsanity.com/paper/1910.06180/) (2019)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [MemNet: A Persistent Memory Network for Image Restoration](https://mlsanity.com/paper/1708.02209/) (2017)
- [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016)
- [From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality](https://mlsanity.com/paper/1912.10088/) (2019)
- [Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images](https://mlsanity.com/paper/2101.02824/) (2021)
- [Neural Nearest Neighbors Networks](https://mlsanity.com/paper/1810.12575/) (2018)
- [Real-world Noisy Image Denoising: A New Benchmark](https://mlsanity.com/paper/1804.02603/) (2018)
- [Probabilistic Noise2Void: Unsupervised Content-Aware Denoising](https://mlsanity.com/paper/1906.00651/) (2019)
- [Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising](https://mlsanity.com/paper/1705.09912/) (2017)
- [Noise2Fast: Fast Self-Supervised Single Image Blind Denoising](https://mlsanity.com/paper/2108.10209/) (2021)

## Built on by (most cited first, 3 of 3)

- [denoiSplit: a method for joint microscopy image splitting and unsupervised denoising](https://mlsanity.com/paper/2403.11854/) (2024)
- [Lightweight Physics-Aware Zero-Shot Ultrasound Plane-Wave Denoising](https://mlsanity.com/paper/2506.21499/) (2025)
- [Type Information-Assisted Self-Supervised Knowledge Graph Denoising](https://mlsanity.com/paper/2503.09916/) (2025)

## Abstract (arXiv)

Recently, denoising methods based on supervised learning have exhibited promising performance. However, their reliance on external datasets containing noisy-clean image pairs restricts their applicability. To address this limitation, researchers have focused on training denoising networks using solely a set of noisy inputs. To improve the feasibility of denoising procedures, in this study, we proposed a single-image self-supervised learning method in which only the noisy input image is used for network training. Gated convolution was used for feature extraction and no-reference image quality assessment was used for guiding the training process. Moreover, the proposed method sampled instances from the input image dataset using Bernoulli sampling with a certain dropout rate for training. The corresponding result was produced by averaging the generated predictions from various instances of the trained network with dropouts. The experimental results indicated that the proposed method achieved state-of-the-art denoising performance on both synthetic and real-world datasets. This highlights the effectiveness and practicality of our method as a potential solution for various noise removal tasks.