High resolution transient/3D imaging technology is of high interest in both scientific research and commercial application. Nowadays, all of the transient imaging methods suffer from low resolution or time consuming mechanical scanning. We proposed a new method based on TCSPC and Compressive Sensing to achieve a high resolution transient imaging with a several seconds capturing process. Picosecond laser sends a serious of equal interval pulse while synchronized SPAD camera's detecting gate window has a precise phase delay at each cycle. After capturing enough points, we are able to make up a whole signal. By inserting a DMD device into the system, we are able to modulate all the frames of data using binary random patterns to reconstruct a super resolution transient/3D image later. Because the low fill factor of SPAD sensor will make a compressive sensing scenario ill-conditioned, We designed and fabricated a diffractive microlens array. We proposed a new CS reconstruction algorithm which is able to denoise at the same time for the measurements suffering from Poisson noise. Instead of a single SPAD senor, we chose a SPAD array because it can drastically reduce the requirement for the number of measurements and its reconstruction time. Further more, it not easy to reconstruct a high resolution image with only one single sensor while for an array, it just needs to reconstruct small patches and a few measurements. In this thesis, we evaluated the reconstruction methods using both clean measurements and the version corrupted by Poisson noise. The results show how the integration over the layers influence the image quality and our algorithm works well while the measurements suffer from non-trival Poisson noise. It's a breakthrough in the areas of both transient imaging and compressive sensing.

Cette thèse aborde la problématique de la restauration d’images 3D de noyaux cellulaires fluorescents issues de la microscopie 2-photons à balayage laser d’animaux observés in vivo et in toto au cours de leur développement embryonnaire. La dégradation originale de ces images provient des limitations des systèmes optiques, du bruit intrinsèque des systèmes de détection ansi que de l’absorption et la diffusion de la lumière dans la profondeur des tissus. A la différence des propositions de “débruitage” de l’état de l’art, nous proposons ici une méthode qui prend en compte les particularités des données biologiques. Cette méthode, adaptation à la troisième dimension d’un algorithme utilisé dans l’analyse d’image astronomique, tire parti de connaissances a priori sur les images étudiées. Les hypothèses émises portent à la fois sur la détérioration du signal par un bruit supposé Mixe Poisson Gaussien (MPG) et sur la nature des objets observés. Nous traitons ici le cas de noyaux de cellules embryonnaires que nous supposons quasi sphériques.L’implémentation en 3D doit prendre en compte les dimensions de la grille d’échantillonnage de l’image. En effet ces dimensions ne sont pas identiques dans les trois directions de l’espace et un objet sphérique échantillonné sur cette grille perd cette caractéristique. Pour adapter notre méthode à une telle grille, nous avons ré-interprété le processus de filtrage, au coeur de la théorie originale, comme un processus physique de diffusion. / In this this document, we present a method to denoise 3D images acquired by 2-photon microscopy and displaying cell nuclei of animal embryos. The specimens are observed in toto and in vivo during their early development. Image deterioration can be explained by the microscope optical flaws, the acquisition system limitations, and light absorption and diffusion through the tissue depth.The proposed method is a 3D adaptation of a 2D method so far applied to astronomical images and it also differs from state-of the of-the-art methods by the introduction of priors on the biological data. Our hypotheses include assuming that noise statistics are Mixed Poisson Gaussian (MPG) and that cell nuclei are quasi spherical.To implement our method in 3D, we had to take into account the sampling grid dimensions which are different in the x, y or z directions. A spherical object imaged on this grid loses this property. To deal with such a grid, we had to interpret the filtering process, which is a core element of the original theory, as a diffusion process.

Heteroscedasticity (or time-dependent volatility) in economic and financial time series has been recognized for decades. Still, heteroscedasticity is surprisingly often neglected by practitioners and researchers. This may lead to inefficient procedures. Much of the work in this thesis is about finding more effective ways to deal with heteroscedasticity in economic and financial data. Paper I suggest a filter that, unlike the Box-Cox transformation, does not assume that the heteroscedasticity is a power of the expected level of the series. This is achieved by dividing the time series by a moving average of its standard deviations smoothed by a Hodrick-Prescott filter. It is shown that the filter does not colour white noise. An appropriate removal of heteroscedasticity allows more effective analyses of heteroscedastic time series. A few examples are presented in Paper II, III and IV of this thesis. Removing the heteroscedasticity using the proposed filter enables efficient estimation of the underlying probability distribution of economic growth. It is shown that the mixed Normal - Asymmetric Laplace (NAL) distributional fit is superior to the alternatives. This distribution represents a Schumpeterian model of growth, the driving mechanism of which is Poisson (Aghion and Howitt, 1992) distributed innovations. This distribution is flexible and has not been used before in this context. Another way of circumventing strong heteroscedasticity in the Dow Jones stock index is to divide the data into volatility groups using the procedure described in Paper III. For each such group, the most accurate probability distribution is searched for and is used in density forecasting. Interestingly, the NAL distribution fits best also here. This could hint at a new analogy between the financial sphere and the real economy, further investigated in Paper IV. These series are typically heteroscedastic, making standard detrending procedures, such as Hodrick-Prescott or Baxter-King, inadequate. Prior to this comovement study, the univariate and bivariate frequency domain results from these filters are compared to the filter proposed in Paper I. The effect of often neglected heteroscedasticity may thus be studied.