One-Pot Multi-Frame Denoising
Not on the map. Why?
Abstract (arXiv)
The performance of learning-based denoising largely depends on clean supervision. However, it is difficult to obtain clean images in many scenes. On the contrary, the capture of multiple noisy frames for the same field of view is available and often natural in real life. Therefore, it is necessary to avoid the restriction of clean labels and make full use of noisy data for model training. So we propose an unsupervised learning strategy named one-pot denoising (OPD) for multi-frame images. OPD is the first proposed unsupervised multi-frame denoising (MFD) method. Different from the traditional supervision schemes including both supervised Noise2Clean (N2C) and unsupervised Noise2Noise (N2N), OPD executes mutual supervision among all of the multiple frames, which gives learning more diversity of supervision and allows models to mine deeper into the correlation among frames. N2N has also been proved to be actually a simplified case of the proposed OPD. From the perspectives of data allocation and loss function, two specific implementations, random coupling (RC) and alienation loss (AL), are respectively provided to accomplish OPD during model training. In practice, our experiments demonstrate that OPD behaves as the SOTA unsupervised denoising method and is comparable to supervised N2C methods for synthetic Gaussian and Poisson noise, and real-world optical coherence tomography (OCT) speckle noise.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 37 of its 86 references that are in the map. First posted on arXiv 18 Feb 2023.
Builds on
37 of 86 references.
References · 37
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2016Densely Connected Convolutional Networkscited by 6,691
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
- 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
- 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
- 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
- 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
25 more
- 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
- 2017Deep Image Priorcited by 1,097
- 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
- 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
- 2018Toward Convolutional Blind Denoising of Real Photographscited by 274
- 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
- 2019ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed datacited by 260
- 2019MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentationcited by 195
- 2019Real Image Denoising with Feature Attentioncited by 176
- 2021Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Imagescited by 171
- 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
- 2017Burst Denoising with Kernel Prediction Networkscited by 156
- 2019Deep Learning on Image Denoising: An overviewcited by 128
- 2019Noisier2Noise: Learning to Denoise from Unpaired Noisy Datacited by 125
- 2018Fully Dense UNet for 2D Sparse Photoacoustic Tomography Artifact Removalcited by 56
- 2017Deep Burst Denoisingcited by 49
- 2019Basis Prediction Networks for Effective Burst Denoising with Large Kernelscited by 46
- 2022CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from Imagecited by 45
- 2021Deep Reparametrization of Multi-Frame Super-Resolution and Denoisingcited by 39
- 2021Speech Denoising Without Clean Training Data: A Noise2Noise Approachcited by 17
- 2019Consensus Neural Network for Medical Imaging Denoising with Only Noisy Training Samplescited by 12
- 2019Multi-Kernel Prediction Networks for Denoising of Burst Imagescited by 8
- 2019Generating Training Data for Denoising Real RGB Images via Camera Pipeline Simulationcited by 6
- 2019Hyperspectral and multispectral image fusion under spectrally varying spatial blurs -- Application to high dimensional infrared astronomical imagingcited by 5
- 2020A Comprehensive Comparison of Multi-Dimensional Image Denoising Methodscited by 5
Built on by
Citing papers per year: 2025: 1.
1 paper.