On learning optimized reaction diffusion processes for effective image restoration

Chen, Yunjin; Yu, Wei; Pock, Thomas

doi:10.1109/cvpr.2015.7299163

Cited by 270 publications

(313 citation statements)

References 36 publications

Supporting

Mentioning

311

Contrasting

Order By: Relevance

“…Discriminative learning methods ( [36], [8], [9], [41], [40]): Previous discriminative learning methods require separate training for each restoration task (denoise, deblur, demosaic) and problem condition (noise levels, blur kernels). This makes it time-consuming and difficult to encompass all tasks and conditions during training.…”

Section: E Connection and Difference With Related Methodsmentioning

confidence: 99%

“…Inspired by the state-of-the-art discriminative methods [8], [9], we propose to learn the model prox Θ , and the fidelity weight scalar λ, from training data. Recall that with our new splitting strategy introduced in Sec.…”

Section: Discriminative Transfer Learningmentioning

confidence: 99%

“…Recently, a number of works [8], [9] have addressed this issue by truncating the iterative optimization and learning discriminative image priors, tailored to a specific reconstruction task (likelihood) and optimization approach. While these methods allow to trade-off quality with the computational budget for a given application, the learned models are highly specialized for the image formation model and noise parameters, in contrast to optimization-based approaches.…”

Section: Introductionmentioning

confidence: 99%

“…Some representative examples of such methods include trainable random field models such as separable Markov random field (MRFSepa) [35] regression tree fields (RTF) [36], cascaded shrinkage fields (CSF) [8], trainable nonlinear reaction diffusion (TRD) models [9] and their extensions [37], [38], [39]. The state-ofthe-art CSF and TRD methods can be derived from the FoE model [30] by unrolling corresponding optimization iterations to be feed-forward networks, where the parameters of each network are trained by minimizing the error between its output images and ground truth for each specific task.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Discriminative Transfer Learning for General Image Restoration

Xiao

Heide

Heidrich

et al. 2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-Recently, several discriminative learning approaches have been proposed for effective image restoration, achieving convincing trade-off between image quality and computational efficiency. However, these methods require separate training for each restoration task (e.g., denoising, deblurring, demosaicing) and problem condition (e.g., noise level of input images). This makes it time-consuming and difficult to encompass all tasks and conditions during training. In this paper, we propose a discriminative transfer learning method that incorporates formal proximal optimization and discriminative learning for general image restoration. The method requires a single-pass discriminative training and allows for reuse across various problems and conditions while achieving an efficiency comparable to previous discriminative approaches. Furthermore, after being trained, our model can be easily transferred to new likelihood terms to solve untrained tasks, or be combined with existing priors to further improve image restoration quality.

show abstract

Section: E Connection and Difference With Related Methodsmentioning

confidence: 99%

Section: Discriminative Transfer Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Discriminative Transfer Learning for General Image Restoration

Xiao

Heide

Heidrich

et al. 2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Methods [17], [18] permit to learn a dictionary to perform denoising via Orthogonal Matching Pursuit (OMP) locally [18] or non-locally [19], [20]. Learning priors via high-order MRF models [22], Gaussian mixture models [3], [11] or shrinkage functions [23], [24] has shown to give interesting results in image denoising. Plain learning via neural networks has shown to give interesting results as well [25].…”

Section: B Learning-based Denoisingmentioning

confidence: 99%

Low-Rankness Transfer for Realistic Denoising

Badri

Yahia

Aboutajdine

2016

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-Current state-of-the-art denoising methods such as non-local low-rank approaches have shown to give impressive results. They are however mainly tuned to work with uniform Gaussian noise corruption and known variance, which is far from the real noise scenario. In fact, noise level estimation is already a challenging problem and denoising methods are quite sensitive to this parameter. Moreover, these methods are based on shrinkage models that are too simple to reflect reality, which results in over-smoothing of important structures such as small-scale text and textures. We propose in this paper a new approach for more realistic image restoration based on the concept of low-rankness transfer (LRT). Given a training clean/noisy image pair, our method learns a mapping between the non-local noisy singular values and the optimal values for denoising to be transfered to a new noisy input. One single image is enough for training the model and can be adapted to the noisy input by taking a correlated image. Experiments conducted on synthetic and real camera noise show that the proposed method leads to an important improvement both visually and in terms of PSNR/SSIM.

show abstract

A deep convolutional neural network using directional wavelets for low‐dose X‐ray CT reconstruction

2017

View full text Add to dashboard Cite

Purpose: Due to the potential risk of inducing cancer, radiation exposure by X-ray CT devices should be reduced for routine patient scanning. However, in low-dose X-ray CT, severe artifacts typically occur due to photon starvation, beam hardening, and other causes, all of which decrease the reliability of the diagnosis. Thus, a high-quality reconstruction method from low-dose X-ray CT data has become a major research topic in the CT community. Conventional model-based de-noising approaches are, however, computationally very expensive, and image-domain de-noising approaches cannot readily remove CT-specific noise patterns. To tackle these problems, we want to develop a new low-dose X-ray CT algorithm based on a deep-learning approach. Method: We propose an algorithm which uses a deep convolutional neural network (CNN) which is applied to the wavelet transform coefficients of low-dose CT images. More specifically, using a directional wavelet transform to extract the directional component of artifacts and exploit the intra-and inter-band correlations, our deep network can effectively suppress CT-specific noise. In addition, our CNN is designed with a residual learning architecture for faster network training and better performance. Results: Experimental results confirm that the proposed algorithm effectively removes complex noise patterns from CT images derived from a reduced X-ray dose. In addition, we show that the wavelet-domain CNN is efficient when used to remove noise from low-dose CT compared to existing approaches. Our results were rigorously evaluated by several radiologists at the Mayo Clinic and won second place at the 2016 "Low-Dose CT Grand Challenge." Conclusions: To the best of our knowledge, this work is the first deep-learning architecture for lowdose CT reconstruction which has been rigorously evaluated and proven to be effective. In addition, the proposed algorithm, in contrast to existing model-based iterative reconstruction (MBIR) methods, has considerable potential to benefit from large data sets. Therefore, we believe that the proposed algorithm opens a new direction in the area of low-dose CT research.

show abstract

On learning optimized reaction diffusion processes for effective image restoration

Cited by 270 publications

References 36 publications

Discriminative Transfer Learning for General Image Restoration

Discriminative Transfer Learning for General Image Restoration

Low-Rankness Transfer for Realistic Denoising

A deep convolutional neural network using directional wavelets for low‐dose X‐ray CT reconstruction

Contact Info

Product

Resources

About