# Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios

arXiv: https://arxiv.org/abs/2303.16783 · HTML: https://mlsanity.com/paper/2303.16783/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 53 references that are in the map.
- First posted on arXiv 29 Mar 2023.

## Builds on (most cited first, 29 of 29)

- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018)
- [Benchmarking Denoising Algorithms with Real Photographs](https://mlsanity.com/paper/1707.01313/) (2017)
- [Multi-level Wavelet-CNN for Image Restoration](https://mlsanity.com/paper/1805.07071/) (2018)
- [Real Image Denoising with Feature Attention](https://mlsanity.com/paper/1904.07396/) (2019)
- [Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images](https://mlsanity.com/paper/2101.02824/) (2021)
- [Understanding Convolution for Semantic Segmentation](https://mlsanity.com/paper/1702.08502/) (2017)
- [High-Quality Self-Supervised Deep Image Denoising](https://mlsanity.com/paper/1901.10277/) (2019)
- [Noisier2Noise: Learning to Denoise from Unpaired Noisy Data](https://mlsanity.com/paper/1910.11908/) (2019)
- [Variational Denoising Network: Toward Blind Noise Modeling and Removal](https://mlsanity.com/paper/1908.11314/) (2019)
- [Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation](https://mlsanity.com/paper/2007.05946/) (2020)
- [AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network](https://mlsanity.com/paper/2203.11799/) (2022)
- [Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization](https://mlsanity.com/paper/2002.11244/) (2020)
- [Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots](https://mlsanity.com/paper/2203.06967/) (2022)
- [NBNet: Noise Basis Learning for Image Denoising with Subspace Projection](https://mlsanity.com/paper/2012.15028/) (2020)
- [Unpaired Learning of Deep Image Denoising](https://mlsanity.com/paper/2008.13711/) (2020)
- [Invertible Denoising Network: A Light Solution for Real Noise Removal](https://mlsanity.com/paper/2104.10546/) (2021)
- [C2N: Practical Generative Noise Modeling for Real-World Denoising](https://mlsanity.com/paper/2202.09533/) (2022)
- [When AWGN-based Denoiser Meets Real Noises](https://mlsanity.com/paper/1904.03485/) (2019)
- [CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from Image](https://mlsanity.com/paper/2203.13009/) (2022)
- [IDR: Self-Supervised Image Denoising via Iterative Data Refinement](https://mlsanity.com/paper/2111.14358/) (2021)
- [Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising](https://mlsanity.com/paper/2303.14934/) (2023)
- [Natural Image Noise Dataset](https://mlsanity.com/paper/1906.00270/) (2019)
- [A Review of an Old Dilemma: Demosaicking First, or Denoising First?](https://mlsanity.com/paper/2004.11577/) (2020)

## Built on by (most cited first, 17 of 17)

- [Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoising](https://mlsanity.com/paper/2412.16460/) (2024)
- [YOND: Practical Blind Raw Image Denoising Free from Camera-Specific Data Dependency](https://mlsanity.com/paper/2506.03645/) (2025)
- [Beyond Image Prior: Embedding Noise Prior into Conditional Denoising Transformer](https://mlsanity.com/paper/2407.09094/) (2024)
- [Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum](https://mlsanity.com/paper/2505.12191/) (2025)
- [Filter2Noise: A Framework for Interpretable and Zero-Shot Low-Dose CT Image Denoising](https://mlsanity.com/paper/2504.13519/) (2025)
- [Blind-Spot Guided Diffusion for Self-supervised Real-World Denoising](https://mlsanity.com/paper/2509.16091/) (2025)
- [FM2S: Towards Spatially-Correlated Noise Modeling in Zero-Shot Fluorescence Microscopy Image Denoising](https://mlsanity.com/paper/2412.10031/) (2024)
- [Unsupervised Real-World Denoising: Sparsity is All You Need](https://mlsanity.com/paper/2503.21377/) (2025)
- [Next-Scale Prediction: A Self-Supervised Approach for Real-World Image Denoising](https://mlsanity.com/paper/2512.21038/) (2025)
- [Why Low-Light Cameras Go Color Blind: Removing Color Bias in Raw Denoising](https://mlsanity.com/paper/2607.11090/) (2026)
- [CDI: Blind Image Restoration Fidelity Evaluation based on Consistency with Degraded Image](https://mlsanity.com/paper/2501.14264/) (2025)
- [Net2Net: When Un-trained Meets Pre-trained Networks for Robust Real-World Denoising](https://mlsanity.com/paper/2510.02733/) (2025)
- [Self-Supervised Compression and Artifact Correction for Streaming Underwater Imaging Sonar](https://mlsanity.com/paper/2511.13922/) (2025)
- [TokEye: Fast Signal Extraction for Fluctuating Time Series via Offline Self-Supervised Learning From Fusion Diagnostics to Bioacoustics](https://mlsanity.com/paper/2602.20317/) (2026)
- [TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Image Denoising](https://mlsanity.com/paper/2604.04484/) (2026)
- [Unpaired Joint Distribution Modeling via Multi-Scale Image Representations](https://mlsanity.com/paper/2607.08198/) (2026)
- [Physics-Driven Independent Pair Generation for Iterative Self-Supervised Low-Dose CT Denoising](https://mlsanity.com/paper/2609.02654/) (2026)

## Abstract (arXiv)

Self-supervised denoising has attracted widespread attention due to its ability to train without clean images. However, noise in real-world scenarios is often spatially correlated, which causes many self-supervised algorithms that assume pixel-wise independent noise to perform poorly. Recent works have attempted to break noise correlation with downsampling or neighborhood masking. However, denoising on downsampled subgraphs can lead to aliasing effects and loss of details due to a lower sampling rate. Furthermore, the neighborhood masking methods either come with high computational complexity or do not consider local spatial preservation during inference. Through the analysis of existing methods, we point out that the key to obtaining high-quality and texture-rich results in real-world self-supervised denoising tasks is to train at the original input resolution structure and use asymmetric operations during training and inference. Based on this, we propose Asymmetric Tunable Blind-Spot Network (AT-BSN), where the blind-spot size can be freely adjusted, thus better balancing noise correlation suppression and image local spatial destruction during training and inference. In addition, we regard the pre-trained AT-BSN as a meta-teacher network capable of generating various teacher networks by sampling different blind-spots. We propose a blind-spot based multi-teacher distillation strategy to distill a lightweight network, significantly improving performance. Experimental results on multiple datasets prove that our method achieves state-of-the-art, and is superior to other self-supervised algorithms in terms of computational overhead and visual effects.