Can fully convolutional networks perform well for general image restoration problems?

Chaudhury, Subhajit; Roy, Hiya

doi:10.23919/mva.2017.7986849

Cited by 23 publications

(20 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, we study the concrete example of denoising an image corrupted by Beta noise. Many algorithms have been developed so far for the removal of additive white Gaussian noise [ 65 , 66 , 67 , 68 , 69 , 70 , 71 , 72 ] which, to some extent, can also be applied for denoising of an image corrupted by Beta noise. However, we here show that the proposed Beta-MCA model is better suited for this task as it assumes a Beta observation noise.…”

Section: Methodsmentioning

confidence: 99%

Inference and Learning in a Latent Variable Model for Beta Distributed Interval Data

Mousavi

Buhl

Guiraud

et al. 2021

Entropy

View full text Add to dashboard Cite

Latent Variable Models (LVMs) are well established tools to accomplish a range of different data processing tasks. Applications exploit the ability of LVMs to identify latent data structure in order to improve data (e.g., through denoising) or to estimate the relation between latent causes and measurements in medical data. In the latter case, LVMs in the form of noisy-OR Bayes nets represent the standard approach to relate binary latents (which represent diseases) to binary observables (which represent symptoms). Bayes nets with binary representation for symptoms may be perceived as a coarse approximation, however. In practice, real disease symptoms can range from absent over mild and intermediate to very severe. Therefore, using diseases/symptoms relations as motivation, we here ask how standard noisy-OR Bayes nets can be generalized to incorporate continuous observables, e.g., variables that model symptom severity in an interval from healthy to pathological. This transition from binary to interval data poses a number of challenges including a transition from a Bernoulli to a Beta distribution to model symptom statistics. While noisy-OR-like approaches are constrained to model how causes determine the observables’ mean values, the use of Beta distributions additionally provides (and also requires) that the causes determine the observables’ variances. To meet the challenges emerging when generalizing from Bernoulli to Beta distributed observables, we investigate a novel LVM that uses a maximum non-linearity to model how the latents determine means and variances of the observables. Given the model and the goal of likelihood maximization, we then leverage recent theoretical results to derive an Expectation Maximization (EM) algorithm for the suggested LVM. We further show how variational EM can be used to efficiently scale the approach to large networks. Experimental results finally illustrate the efficacy of the proposed model using both synthetic and real data sets. Importantly, we show that the model produces reliable results in estimating causes using proofs of concepts and first tests based on real medical data and on images.

show abstract

Section: Methodsmentioning

confidence: 99%

Inference and Learning in a Latent Variable Model for Beta Distributed Interval Data

Mousavi

Buhl

Guiraud

et al. 2021

Entropy

View full text Add to dashboard Cite

show abstract

“…Köhler et al 22 showed a mask specific deep neural network-based blind inpainting technique for filling in small missing regions in an image. Chaudhury et al 23 attempted to solve this problem by proposing a lightweight fully convolutional network and demonstrated that their method can achieve comparable performance as the sparse coding-based K-singular value decomposition 24 technique. However, these inpainting approaches were limited to very small sized masks.…”

Section: Deep Learning-based Inpaintingmentioning

confidence: 99%

Image inpainting using frequency-domain priors

et al. 2021

Self Cite

View full text Add to dashboard Cite

We present an image inpainting technique using frequency-domain information.Prior works on image inpainting predict the missing pixels by training neural networks using only the spatial-domain information. However, these methods still struggle to reconstruct highfrequency details for real complex scenes, leading to a discrepancy in color, boundary artifacts, distorted patterns, and blurry textures. To alleviate these problems, we investigate if it is possible to obtain better performance by training the networks using frequency-domain information (discrete Fourier transform) along with the spatial-domain information. To this end, we propose a frequency-based deconvolution module that enables the network to learn the global context while selectively reconstructing the high-frequency components. We evaluate our proposed method on the publicly available datasets: celebFaces attribute (CelebA) dataset, Paris streetview, and describable textures dataset and show that our method outperforms current stateof-the-art image inpainting techniques both qualitatively and quantitatively. © The Authors.Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

“…Kohler et al [54] showed a mask specific deep neural network-based blind inpainting technique for filling in small missing regions in an image. Chaudhury et al [58] attempted to solve the blind image inpainting task using a lightweight fully convolutional network (FCN) demonstrating a comparable performance with the sparse coding based k singular value decomposition (K-SVD) [59] technique. However, initially, CNN-based image inpainting approaches were limited to very small sized masks.…”

Section: Cnn-based Inpaintingmentioning

confidence: 99%