Learning to do multiframe wavefront sensing unsupervisedly: applications to blind deconvolution

• URL: http://arxiv.org/abs/2006.01438v2
• Date: Sun, 20 Dec 2020 11:33:48 GMT
• Title: Learning to do multiframe wavefront sensing unsupervisedly: applications to blind deconvolution
• Authors: A. Asensio Ramos (IAC, ULL), N. Olspert (MPS)
• Abstract summary: We propose an unsupervised training scheme for blind deconvolution deep learning systems. It can be applied for the correction of point-like as well as extended objects. The network model is roughly three orders of magnitude faster than applying standard deconvolution.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Observations from ground based telescopes are affected by the presence of the Earth atmosphere, which severely perturbs them. The use of adaptive optics techniques has allowed us to partly beat this limitation. However, image selection or post-facto image reconstruction methods applied to bursts of short-exposure images are routinely needed to reach the diffraction limit. Deep learning has been recently proposed as an efficient way to accelerate these image reconstructions. Currently, these deep neural networks are trained with supervision, so that either standard deconvolution algorithms need to be applied a-priori or complex simulations of the solar magneto-convection need to be carried out to generate the training sets. Our aim here is to propose a general unsupervised training scheme that allows multiframe blind deconvolution deep learning systems to be trained simply with observations. The approach can be applied for the correction of point-like as well as extended objects. Leveraging the linear image formation theory and a probabilistic approach to the blind deconvolution problem produces a physically-motivated loss function. The optimization of this loss function allows an end-to-end training of a machine learning model composed of three neural networks. As examples, we apply this procedure to the deconvolution of stellar data from the FastCam instrument and to solar extended data from the Swedish Solar Telescope. The analysis demonstrates that the proposed neural model can be successfully trained without supervision using observations only. It provides estimations of the instantaneous wavefronts, from which a corrected image can be found using standard deconvolution technniques. The network model is roughly three orders of magnitude faster than applying standard deconvolution based on optimization and shows potential to be used on real-time at the telescope.

Related papers

• Solar multi-object multi-frame blind deconvolution with a spatially variant convolution neural emulator [0.0]
  This paper introduces a novel framework leveraging a deep neural network to emulate spatially variant convolutions. By training on a dataset of images convolved with spatially invariant point spread functions, this approach presents a significant advancement over traditional methods.
  arXiv  Detail & Related papers  (2024-05-16T07:42:39Z)
• Self-STORM: Deep Unrolled Self-Supervised Learning for Super-Resolution Microscopy [55.2480439325792]
  We introduce deep unrolled self-supervised learning, which alleviates the need for such data by training a sequence-specific, model-based autoencoder. Our proposed method exceeds the performance of its supervised counterparts.
  arXiv  Detail & Related papers  (2024-03-25T17:40:32Z)
• Leveraging Classic Deconvolution and Feature Extraction in Zero-Shot Image Restoration [0.4398130586098371]
  Non-blind deconvolution aims to restore a sharp image from its blurred counterpart given an obtained kernel. We propose a novel non-blind deconvolution method that leverages the power of deep learning and classic iterative deconvolution algorithms. Our method demonstrates significant improvements in various real-world applications non-blind deconvolution tasks.
  arXiv  Detail & Related papers  (2023-10-03T14:41:30Z)
• Self-Supervised Single-Image Deconvolution with Siamese Neural Networks [6.138671548064356]
  Inverse problems in image reconstruction are fundamentally complicated by unknown noise properties. Deep learning methods allow for flexible parametrization of the noise and learning its properties directly from the data. We tackle this problem with Fast Fourier Transform convolutions that provide training speed-up in 3D deconvolution tasks.
  arXiv  Detail & Related papers  (2023-08-18T09:51:11Z)
• Accelerating Multiframe Blind Deconvolution via Deep Learning [0.0]
  Ground-based solar image restoration is a computationally expensive procedure. We propose a new method to accelerate the restoration based on algorithm unrolling. We show that both methods significantly reduce the restoration time compared to the standard optimization procedure.
  arXiv  Detail & Related papers  (2023-06-21T07:53:00Z)
• Efficient data-driven gap filling of satellite image time series using deep neural networks with partial convolutions [0.0]
  This paper shows how three-dimensional partial convolutions can be used as layers in neural networks to fill gaps in satellite image time series. To evaluate the approach we apply a U-Net-like model on incomplete time series of quasi-global carbon monoxide observations from the Sentinel-5P satellite.
  arXiv  Detail & Related papers  (2022-08-18T11:32:04Z)
• InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering [55.70938412352287]
  We present an information-theoretic regularization technique for few-shot novel view synthesis based on neural implicit representation. The proposed approach minimizes potential reconstruction inconsistency that happens due to insufficient viewpoints. We achieve consistently improved performance compared to existing neural view synthesis methods by large margins on multiple standard benchmarks.
  arXiv  Detail & Related papers  (2021-12-31T11:56:01Z)
• Learning Discriminative Shrinkage Deep Networks for Image Deconvolution [122.79108159874426]
  We propose an effective non-blind deconvolution approach by learning discriminative shrinkage functions to implicitly model these terms. Experimental results show that the proposed method performs favorably against the state-of-the-art ones in terms of efficiency and accuracy.
  arXiv  Detail & Related papers  (2021-11-27T12:12:57Z)
• Is Deep Image Prior in Need of a Good Education? [57.3399060347311]
  Deep image prior was introduced as an effective prior for image reconstruction. Despite its impressive reconstructive properties, the approach is slow when compared to learned or traditional reconstruction techniques. We develop a two-stage learning paradigm to address the computational challenge.
  arXiv  Detail & Related papers  (2021-11-23T15:08:26Z)
• Auto-Rectify Network for Unsupervised Indoor Depth Estimation [119.82412041164372]
  We establish that the complex ego-motions exhibited in handheld settings are a critical obstacle for learning depth. We propose a data pre-processing method that rectifies training images by removing their relative rotations for effective learning. Our results outperform the previous unsupervised SOTA method by a large margin on the challenging NYUv2 dataset.
  arXiv  Detail & Related papers  (2020-06-04T08:59:17Z)
• Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation [60.80172153614544]
  Un-trained convolutional neural networks have emerged as highly successful tools for image recovery and restoration. We show that an un-trained convolutional neural network can approximately reconstruct signals and images that are sufficiently structured, from a near minimal number of random measurements.
  arXiv  Detail & Related papers  (2020-05-07T15:57:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.