Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image Prior

Zhussip, Magauiya; Soltanayev, Shakarim; Chun, Se Young

doi:10.1109/cvpr.2019.01050

Cited by 46 publications

(20 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There has also been interest in algorithms that leverage the statistical modeling capabilities of neural networks [52]- [55]. VDAMP with a neural network denoiser g(r k ; τ k ) could accommodate ground-truth free training by using cSURE as the loss, as shown for AMP in [56], [57].…”

Section: Discussionmentioning

confidence: 99%

Approximate Message Passing With a Colored Aliasing Model for Variable Density Fourier Sampled Images

Millard¹,

Hess²,

Mailhé³

et al. 2020

IEEE Open J. Signal Process.

View full text Add to dashboard Cite

The Approximate Message Passing (AMP) algorithm efficiently reconstructs signals which have been sampled with large i.i.d. sub-Gaussian sensing matrices. Central to AMP is its "state evolution", which guarantees that the difference between the current estimate and ground truth (the "aliasing") at every iteration obeys a Gaussian distribution that can be fully characterized by a scalar. However, when Fourier coefficients of a signal with non-uniform spectral density are sampled, such as in Magnetic Resonance Imaging (MRI), the aliasing is intrinsically colored, AMP's scalar state evolution is no longer accurate and the algorithm encounters convergence problems. In response, we propose the Variable Density Approximate Message Passing (VDAMP) algorithm, which uses the wavelet domain to model the colored aliasing. We present empirical evidence that VDAMP obeys a "colored state evolution", where the aliasing obeys a Gaussian distribution that can be fully characterized with one scalar per wavelet subband. A benefit of state evolution is that Stein's Unbiased Risk Estimate (SURE) can be effectively implemented, yielding an algorithm with subbanddependent thresholding that has no free parameters. We empirically evaluate the effectiveness of VDAMP on three variations of Fast Iterative Shrinkage-Thresholding (FISTA) and find that it converges in around 10 times fewer iterations on average than the next-fastest method, and typically a lower mean-squared-error.

show abstract

Section: Discussionmentioning

confidence: 99%

Approximate Message Passing With a Colored Aliasing Model for Variable Density Fourier Sampled Images

Millard¹,

Hess²,

Mailhé³

et al. 2020

IEEE Open J. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Accurate distortion distance estimation is important for determining the weights of the deep network [35]. For the learned regularization term, we use a well-trained residual-regressive network that can accurately determine the distortion distance σ. Additionally, the proximal operator plays an important role in the PMGD algorithm.…”

Section: A Adaptive Proximal Operator Selectionmentioning

confidence: 99%

Deep-Learned Regularization and Proximal Operator for Image Compressive Sensing

Chen

Guo

Feng

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Deep learning has recently been intensively studied in the context of image compressive sensing (CS) to discover and represent complicated image structures. These approaches, however, either suffer from nonflexibility for an arbitrary sampling ratio or lack an explicit deep-learned regularization term. This paper aims to solve the CS reconstruction problem by combining the deep-learned regularization term and proximal operator. We first introduce a regularization term using a carefully designed residual-regressive net, which can measure the distance between a corrupted image and a clean image set and accurately identify to which subspace the corrupted image belongs. We then address a proximal operator with a tailored dilated residual channel attention net, which enables the learned proximal operator to map the distorted image into the clean image set. We adopt an adaptive proximal selection strategy to embed the network into the loop of the CS image reconstruction algorithm. Moreover, a self-ensemble strategy is presented to improve CS recovery performance. We further utilize state evolution to analyze the effectiveness of the designed networks. Extensive experiments also demonstrate that our method can yield superior accurate reconstruction (PSNR gain over 1 dB) compared to other competing approaches while achieving the current state-of-the-art image CS reconstruction performance. The test code is available at https://github.com/zjut-gwl/CSDRCANet.

show abstract

“…The unsupervised learning of denoising algorithms (i.e, when A = I) have been extensively studied, resulting in popular schemes such as Noise2Noise [19] and Noise2Void [20]. Recently, several researchers have adapted the Stein's unbiased risk estimate (SURE) [14] for the unsupervised training of deep image denoisers [16,18]. When C = σ 2 I, SURE methods use an unbiased estimate of the mean-square error (MSE) as…”

Section: Unsupervised Learning For Denoisingmentioning

confidence: 99%

“…A challenge in directly using GSURE to train deep image reconstruction algorithm in an end-to-end fashion is the poor approximation of the MSE by the projected MSE, especially in compressed sensing applications [16]. Hence, the LDAMP-SURE [16] algorithm relies on training different denoisers at each iteration in a message-passing iterative algorithm using the SURE loss [16,18].…”

Section: Introductionmentioning

confidence: 99%

Ensure: Ensemble Stein’s Unbiased Risk Estimator for Unsupervised Learning

Aggarwal

Pramanik

Jacob

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Deep learning algorithms are emerging as powerful alternatives to compressed sensing methods, offering improved image quality and computational efficiency. Unfortunately, fully sampled training images may not be available or are difficult to acquire in several applications, including high-resolution and dynamic imaging. Previous studies in image reconstruction have utilized Stein's Unbiased Risk Estimator (SURE) as a mean square error (MSE) estimate for the image denoising step in an unrolled network. Unfortunately, the end-to-end training of a network using SURE remains challenging since the projected SURE loss is a poor approximation to the MSE, especially in the heavily undersampled setting. We propose an ENsemble SURE (ENSURE) approach to train a deep network only from undersampled measurements. In particular, we show that training a network using an ensemble of images, each acquired with a different sampling pattern, can closely approximate the MSE. Our preliminary experimental results show that the proposed ENSURE approach gives comparable reconstruction quality to supervised learning and a recent unsupervised learning method.

show abstract

Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image Prior

Cited by 46 publications

References 37 publications

Approximate Message Passing With a Colored Aliasing Model for Variable Density Fourier Sampled Images

Approximate Message Passing With a Colored Aliasing Model for Variable Density Fourier Sampled Images

Deep-Learned Regularization and Proximal Operator for Image Compressive Sensing

Ensure: Ensemble Stein’s Unbiased Risk Estimator for Unsupervised Learning

Contact Info

Product

Resources

About