Abstract-Deblurring noisy Poisson images has recently been subject of an increasingly amount of works in many areas such as astronomy or biological imaging. In this paper, we focus on confocal microscopy which is a very popular technique for 3D imaging of biological living specimens which gives images with a very good resolution (several hundreds of nanometers), even though degraded by both blur and Poisson noise. Deconvolution methods have been proposed to reduce these degradations and we focus in this paper on techniques which promote the introduction of explicit prior on the solution. One difficulty of these techniques is to set the value of the parameter which weights the trade-off between the data term and the regularizing term. Actually, only few works have been devoted to the research of an automatic selection of this regularizing parameter when considering Poisson noise so it is often set manually such that it gives the best visual results. We present here two recent methods to estimate this regularizing parameter and we first propose an improvement of these estimators which takes advantage of confocal images. Following these estimators, we secondly propose to express the problem of Poisson noisy images deconvolution as the minimization of a new constrained problem. The proposed constrained formulation is well suited to this application domain since it is directly expressed using the anti log-likelihood of the Poisson distribution and therefore does not require any approximation. We show how to solve the unconstrained and constrained problem using the recent Alternating Direction technique and we present results on synthetic and real data using well-known priors such as Total Variation and wavelet transforms. Among these wavelet transforms, we specially focus on the Dual-Tree Complex Wavelet transform and on the dictionary composed of Curvelets and undecimated wavelet transform.

Recently, convolutional neural networks have been successfully applied to lossy image compression. End-to-end optimized autoencoders, possibly variational, are able to dramatically outperform traditional transform coding schemes in terms of rate-distortion trade-off; however, this is at the cost of a higher computational complexity. An intensive training step on huge databases allows autoencoders to learn jointly the image representation and its probability distribution, possibly using a non-parametric density model or a hyperprior auxiliary autoencoder to eliminate the need for prior knowledge. However, in the context of on board satellite compression, time and memory complexities are submitted to strong constraints. The aim of this paper is to design a complexity-reduced variational autoencoder in order to meet these constraints while maintaining the performance. Apart from a network dimension reduction that systematically targets each parameter of the analysis and synthesis transforms, we propose a simplified entropy model that preserves the adaptability to the input image. Indeed, a statistical analysis performed on satellite images shows that the Laplacian distribution fits most features of their representation. A complex non parametric distribution fitting or a cumbersome hyperprior auxiliary autoencoder can thus be replaced by a simple parametric estimation. The proposed complexity-reduced autoencoder outperforms the Consultative Committee for Space Data Systems standard (CCSDS 122.0-B) while maintaining a competitive performance, in terms of rate-distortion trade-off, in comparison with the state-of-the-art learned image compression schemes.

Deblurring noisy Poisson images has recently been subject of an increasingly amount of works in many areas such as astronomy or biological imaging. Several methods have promoted explicit prior on the solution to regularize the ill-posed inverse problem and to improve the quality of the image. In each of these methods, a regularizing parameter is introduced to control the weight of the prior. Unfortunately, this regularizing parameter has to be manually set such that it gives the best qualitative results. To tackle this issue, we present in this paper two constrained formulations for the Poisson deconvolution problem, derived from recent advances in regularizing parameter estimation for Poisson noise. We first show how to improve the accuracy of these estimators and how to link these estimators to constrained formulations. We then propose an algorithm to solve the resulting optimization problems and detail how to perform the projections on the constraints. Results on real and synthetic data are presented.

Deblurring images corrupted by Poisson noise is a challenging process which has devoted much research in many applications such as astronomical or biological imaging. This problem, among others, is an ill-posed problem which can be regularized by adding knowledge on the solution. Several methods have therefore promoted explicit prior on the image, coming along with a regularizing parameter to moderate the weight of this prior. Unfortunately, in the domain of Poisson deconvolution, only a few number of methods have been proposed to select this regularizing parameter which is most of the time set manually such that it gives the best visual results. In this paper, we focus on the use of l 1-norm prior and present two methods to select the regularizing parameter. We show some comparisons on synthetic data using classical image fidelity measures.

Earth observation through satellite images is crucial to help economic activities as well as to monitor the impact of human activities on ecosystems. Current satellite systems are subjected to strong computational complexity constraints. Thus, image compression is perfomed onboard with specifically tailored algorithms while image denoising is performed on the ground. In this letter, we intend to address satellite image compression and denoising with neural networks. The first proposed approach uses a single neural architecture for joint onboard compression and denoising. The second proposed approach sequentially uses a first neural architecture for onboard compression and a second one for on ground denoising. For both approaches, the onboard architectures are lightened as much as possible, following the procedure proposed in [1]. The two approaches are shown to outperform the current satellite imaging system and their respective pros and cons are discussed.