• Corpus ID: 239616142

Self-supervised denoising for massive noisy images

  title={Self-supervised denoising for massive noisy images},
  author={Feng Wang and Trond R. Henninen and Debora Keller and Rolf Erni},
We propose an effective deep learning model for signal reconstruction, which requires no signal prior, no noise model calibration, and no clean samples. This model only assumes that the noise is independent of the measurement and that the true signals share the same structured information. We demonstrate its performance on a variety of real-world applications, from sub-Ångström resolution atomic images to sub-arcsecond resolution astronomy images. 


Noise2Noise: Learning Image Restoration without Clean Data
It is shown that under certain common circumstances, it is possible to learn to restore signals without ever observing clean ones, at performance close or equal to training using clean exemplars.
High-Quality Self-Supervised Deep Image Denoising
This work builds on a recent technique that removes the need for reference data by employing networks with a "blind spot" in the receptive field, and significantly improves two key aspects: image quality and training efficiency.
Noise2Self: Blind Denoising by Self-Supervision
A general framework for denoising high-dimensional measurements which requires no prior on the signal, no estimate of the noise, and no clean training data is proposed, which allows us to calibrate $\mathcal{J}$-invariant versions of any parameterised Denoising algorithm, from the single hyperparameter of a median filter to the millions of weights of a deep neural network.
Self2Self With Dropout: Learning Self-Supervised Denoising From Single Image
A self-supervised learning method which only uses the input noisy image itself for training, which significantly outperforms existing single-image learning or non-learning methods, and is competitive to the denoising networks trained on external datasets.
A non-local algorithm for image denoising
  • A. Buades, B. Coll, J. Morel
  • Computer Science, Mathematics
    2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
A new measure, the method noise, is proposed, to evaluate and compare the performance of digital image denoising methods, and a new algorithm, the nonlocal means (NL-means), based on a nonlocal averaging of all pixels in the image is proposed.
Deep Neural Network Convolution for Natural Image Denoising
A deep neural network for natural image denoising which was hundred-layer deep, exploited both internal and external residual learning, and was trained in an image-based fashion is designed.
Hierarchical residual learning for image denoising
Experimental results on several datasets show that the proposed hierarchical residual learning based CNN framework for image denoising method outperforms many state-of-the-art ones.
Multi-resolution convolutional neural networks for inverse problems
This work proposes a novel, fast-converging neural network architecture capable of solving generic image(s)-to-image(s) inverse problems relevant to a diverse set of domains and shows it is useful in recovering wavefronts from direct intensity measurements, imaging objects from diffusely reflected images, and denoising scanning transmission electron microscopy images, just by using different training datasets.
Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
This work clearly establishes the value of using a denoising criterion as a tractable unsupervised objective to guide the learning of useful higher level representations.
Noise2Atom: unsupervised denoising for scanning transmission electron microscopy images
This work proposes consecutive structural similarity (CSS) for image quality assessment, based on the fact that the structures remain much the same as the previous frame(s) within small scan intervals, and demonstrates the superiority of the model by providing evaluation in terms of CSS and visual quality on different experimental datasets.