ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements

By Kuldeep Kulkarni, Suhas Lohit, Pavan K. Turaga, Ronan Kerviche, Amit Ashok. Computer Vision and Pattern Recognition, 2016

714 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c58a7dc8f84df5089797d43dd218c40093d1f3c8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing (2017, methodology): “For testing, we utilize two widely used benchmark datasets: Set11 [21] and BSD68 [27], which have 11 and 68 gray images, respectively.”
A Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction (2017, methodology): “In fact, CNNs have already been applied to compressed sensing from random Gaussian measurements [11].”
ADMM-CSNet: A Deep Learning Approach for Image Compressive Sensing (2020, methodology): “In [33], [43], [44], fullyconnected deep networks or deep convolutional nets were”
AMP-Net: Denoising-Based Deep Unfolding for Compressive Image Sensing (2020, methodology): “prior more ﬂexible and intuitive with fewer demanded parameters. Besides, in CS systems, visual images are commonly sampled block by block and reconstructed by processing each image block [44], [26], [27], [34]. However, for these block-based methods, additional deblocking operations must be applied”
Flash Photography for Data-Driven Hidden Scene Recovery (2018, methodology): “Data-driven techniques have also been applied to problems in the computational imaging community such as phase imaging [34], compressive imaging [25], tomography [22], microscopy [18], imaging [17], and imaging through scattering media [31].”
Rank Minimization for Snapshot Compressive Imaging (2018, methodology): “Most recently, the deep learning algorithms have been used in CS inversion [63], [64], [65] and as mentioned in the introduction, deep learning has been employed for video CS in [30], [31] (but with some constraints).”
One Network to Solve Them All — Solving Linear Inverse Problems Using Deep Projection Models (2017, methodology): “Such methods have achieved state-of-the-art performance in many challenging image inverse problems like super-resolution [17, 29], inpainting [38], compressive sensing [28, 35, 36], and image debluring [49].”
Solving Linear Inverse Problems Using Gan Priors: An Algorithm with Provable Guarantees (2018, methodology): “This approach is used in [28, 29, 30, 31, 32, 33] to solve different inverse problems, and has met with considerable success.”
Deep speckle correlation: a deep learning approach toward scalable imaging through scattering media (2018, background): “…powerful in solving complex imaging problems, providing performance surpassing those using state-of-the-art model-based techniques [34], such as super-resolution [43, 57], deconvolution [58, 61], compressive imaging [27, 60], tomography [19], holography [42,44], and phase recovery [37,50].”
Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods (2018, methodology): “[18] use a CNN with six convolutional layers to obtain an intermediate reconstruction of the input CS measurements, which is then further refined with a non deep learning based denoising method.”
Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing (2019, result): “For instance, ADMM-CSNet [12] has shown to be about twice as fast as ReconNet [45], while DUBLID [29] is almost two times faster than DeblurGAN [46].”
Deep Convolutional Neural Network for Inverse Problems in Imaging (2016, background): “Moreover, regression-type neural networks demonstrated impressive results on inverse problems with exact models such as signal denoising [21], [22], deconvolution [23], artifact reduction [24], [25], signal recovery (model-based restoration) [26], [27], and interpolation [28]– [30].”
Deep Generalized Unfolding Networks for Image Restoration (2022, methodology): “For instance, there are 2 dB gains compared with OPINENet + [86] on the Set11 test set, with the CS ratio being 1% .”
Learned D-AMP: Principled Neural Network based Compressive Image Recovery (2017, methodology): “d measurements. Other papers in this line of work have used either pure convolutional layers (DeepInverse [15]) or a combination of convolutional and fully connected layers (DR2-Net [16] and ReconNet [14]) to build deep learning frameworks capable of solving the CS recovery problem. As demonstrated ”
Face De-Spoofing: Anti-Spoofing via Noise Modeling (2018, methodology): “Our approach is motivated by the classic image de-X problems, such as image de-noising and de-blurring [9,10,11,12].”