The aim of realistic digital imaging is the creation of high quality imagery, which faithfully represents the physical environment. The ultimate goal is to create images, which are perceptually indistinguishable from a real scene. The RealVision network brings together leading universities, centers focused on industrial development and companies in Multimedia, Optics, Visual Communication, Visual Computing, Computer Graphics and Human Vision research across Europe, with the aim of training a new generation of scientists, technologists, and entrepreneurs that will move Europe into a leading role in innovative hyper-realistic imaging technologies. Current imaging technologies capture only a fraction of visual information that the human eye can see. The colours and dynamic range are inadequate for most real-world scenes and not all depth cues required for natural 3D vision are captured. This limits the realism of the experience and has hampered the introduction of 3D technology. Advancement in imaging technologies makes it possible to circumvent these bottlenecks in visual systems. As a result, new visual signal-processing areas have emerged such as light fields, ultra-high definition, highframe rate and high dynamic range imaging. The novel combinations of those technologies can facilitate a hyper-realistic visual experience. This will without doubt be the future frontier for new imaging systems. However there are several technological barriers that need to be overcome as well as challenges in what are the best solutions perceptually. The goal of this network is to combine expertise from several disciplines as engineering, computer science, physics, vision science and psychology – usually disconnected – and train ESRs to be capable of working with all stages and aspects of visual processing to overcome existing interdisciplinary and intersectorial barriers to efficiently develop truly perceptually better visual imaging systems.

This research program deals with the quality enhancement of digital images. Specifically, we consider the increasingly common situations where several acquisitions of the same scene are available, possibly through a video sequence. An issue of growing importance is to fuse these images in order to get a single enhanced image. Another crucial question concerns the joint restoration of several images of the same sequence. Such an approach has two great advantages. First, going beyond the physical limitations of sensors becomes possible, in terms of dynamic range, resolution or signal- to-noise ratio. Second, the classical limitations of single shot imaging (blur, specular reflections, over or under-exposure, etc.) may be strongly attenuated. As a counterpart, multi-image restoration faces specific difficulties, the toughest of which are related to change detection, motion detection, outliers (aberrant pixels or regions) detection, inpainting, contrast and colour corrections. The proposed work program gathers several classical problems from image processing together with complex issues in image analysis and comparisons. It builds on various mathematical tools, mainly statistical estimation, optimization, stochastic modeling, variational approaches and optimal transport. Within this program, our main goal will be to develop reliable and efficient numerical algorithms for each of the studied restoration modalities.

L'image relief est là. Les cinéastes et les majors d'Hollywood multiplient les projets de films et prévoient la conversion de milliers de salles 3D numériques 2K. Les partenaires de ce projet, riches de leurs expériences et développements antérieurs, ont décidé de proposer aux réalisateurs européens les moyens de maîtriser véritablement la mise en scène du relief. Ceci implique la mise en place d'outils performants, couvrant la totalité d'une chaîne de fabrication du Relief Progressif Haute Définition, de la prise de vues à la post production. L'ergonomie, la facilité d'utilisation, l'intégration de réglages instantanés et la maniabilité doivent réduire au maximum les contraintes qui entourent habituellement la prise de vues en relief. Nous serons alors en mesure d'assurer, dans les meilleures conditions, les tournages de films IMAX 3D ou longs métrages relief.